Yes, there are standards for translation – but they are expensive and, at least for freelance translators, perhaps only of moderate interest. However, it may still be useful to be reasonably familiar with them. You should also know that they apply to requirements and responsibilities, not to the results.

Ingemar Strandvik – Quality Manager at the European Commission’s Translation Directorate – is a friend of standardization, even when it comes to something fundamentally as ephemeral as translation. In his presentation, Why standards can benefit translators (2017), he says that standards can contribute the following:

Definition of quality of service provision:

• Compliance with requirements; meeting needs and expectations ð specifications

Distilled wisdom of the profession, best practice:

• process focus, competencies, workflow steps

Benchmarks, references, check lists:

• codification of translators’ common sense
• legal translation with[out] translation training
• presented in an authoritative way ð credibility, assertiveness, improved communication

What is a Standard?

On the definition of the term “standard”, Ingemar Strandvik has found the following quote: “in short, a standard is an agreed wayof doing something . This may include the manufacture of a product, the administration of a process, the delivery of a service or of materials – standards can cover a huge range of operations performed by organizations and used by their customers.”

Standards of interest to us translators are (the links are to free sample pages):

• ISO/TS 11669:2012, Translation projects – General guidance (technical report)
• ISO 17100:2015, Translation Services – Requirements for translation services
• ISO 18587:2017, Translation services – Post-editing of machine translation output – Requirements
• ISO 20771:2020, Legal translation – Requirements
• ISO 5060:2024, Evaluation of Translation Output

Furthermore, a project to standardize quality assessment, Translation services – Assessment of translation output – General guidance (ISO 50960-#), was recently launched. See below.

Note: In the ATA Chronicle for Sept/Oct 2021, there is an interesting article on ISO standards and information security: Is Applying ISO Standards to Information Security the New Black in Translation?.

To what use?

A standard can basically be used in two ways: As information on processes (“good practice”) and requirements, and for qualification through certification. The latter is an expensive process and is normally only relevant for translation agencies of some size. I have never heard of a company (translation agency or direct customer) that required a freelance translator to be certified. And a quick survey among a dozen Swedish agencies suggests that only one of them is certified (then against ISO 17100); most have never experienced a demand for certification, and many do not even know the existence of any of these standards.

As regards standards as a basis for (further) training, no doubt the freelance translator may find useful information. But their main focus is the translation agency, which may well want to inform on the requirements that the standard imposes on the subcontractor. If a freelancer wants spend money on this form of training, I would actually recommend the technical report for translation projects even though it is by far the most expensive one.

In any case, general knowledge may well be useful, so here is a summary of the contents.

ISO/TS 11669

The most comprehensive standard is the general guidance for translation projects, ISO/TS 11669. Formally, it is not a standard but a “technical specification”, which means, among other things, that it cannot be certified against. Furthermore, it is much more detailed than a regular standard: “An organizing principle of this Technical Specification is the importance of structured specifications in translation projects. … A system is described for making decisions about how translation projects are to be carried out. … In practice, requesters do not always provide project specifications … [but] Requesters and TSPs should work together to determine project specifications. … When both requesters and TSPs agree on project specifications, the quality of a translation … can be determined by the degree to which the target content adheres to the predetermined specifications.” Also, these specifications are “the starting point for all assessments, both qualitative and quantitative”.

A major point here is that the specifications are crucial to the assessment of the quality of a translation. Not surprisingly, more than half of the standardʼs instructions relate to the preparation of structured specifications for translation projects. They include comprehensive lists and descriptions of parameters – almost 40 of them, including sub-parameters. Examples are production tasks, which consist of “typical production tasks”: Preparation, Initial translation, In-process quality assurance [consisting of self-checking, revision, review, final formatting, and proofreading], and “additional tasks”.

Note: For the preparation of project specifications (a neglected area), see this excellent (and easy to read) document from the European Commission: Translation Quality Info Sheets for Contractors.

Other parts of the standard include a chapter on Working together – Requesters and translation service providers (TSPs); this includes definitions of freelance translators as a translation provider, as well as the competencies of translators and professionals – see the box below. A chapter on Translation project management and, finally, a chapter on Phases of the translation project. The latter is particularly detailed. Especially notable here is a whole page on “post-production”, including feedback from the end user – the same element is covered in the corresponding standard, ISO 17100, in seven lines!

Obviously, this standard is primarily aimed at translation agencies. To me, it is just as obvious that it is little applied by them only to a minor extent. One would expect it to be reflected in the instructions to the subcontractors/freelancers, but I have never seen that. I think that most agencies would find quite a lot of useful stuff here; there is probably very little that its authors have missed.

ISO 17100

The step from ISO/TS 11669 to ISO 17100 is not big; the latter is, as I said, the corresponding standard, against which certification can be done, and it concerns translation service requirements. Here we find the “normal ingredient”, the chapter on competencies and qualifications (see box below). Thereafter follow processes and measures prior to production, including quotation and contract as well as preparations. Then there is a chapter on the production process: Project management, translation process (translation, control, checking reading, peer review, Proofreading and final verification and approval for delivery). And finally, a short chapter on “processes after delivery”. (“[the agency] should forward feedback from customers to all interested parties” – but how many freelancers hear about the end customer’s reactions?)

There are also six “informative” annexes (informative as opposed to normative, i.e. the annexes are not included in the certification requirements), including Agreements and project specifications, as well as Project registration and project reporting – thus they should be seen as suggestions on what could be included.

ISO 20771

Related to ISO 17100 is ISO 20771, i.e. requirements relating to the translation of legal texts. It applies to translation that is law-related or falls within the legal domain, in terms of both content and context. It is pointed out that “legal translators” may be subject to specific requirements regarding professionalism, confidentiality and ethics, as well as procedures relating to authorization, certification and safety approval. And unlike ISO 17100 – which focuses primarily on agencies – this standard is primarily intended for individual translators. If you are a freelance translator interested in certification, this is probably the standard which would be of primary use for you.

The usual section on competences and qualifications is comparatively detailed and includes requirements for “recognized degrees” in language, translation or legal – a requirement which, unlike the ISO 17100 requirements, cannot be replaced by at least five years of professional experience.

Furthermore, the responsibility of the legal translator is described in detail, and this applies even more to the elements Agreement and service specification, Translation, Check, Revision and review, Verification and correction, Signing off and record keeping, Authorized certification, Complaints, individual responsibility and corrective action. Of course there is also a chapter on Confidentiality, security and professional liability insurance – and finally on Professional development and involvement. There is also an Annex with “Information on authorized legal translation used in judicial settings,  and for the use of public authorities and commercial purposes”.

ISO 18587

Probably of more general interest is ISO 18587, which applies to requirements for post-editing of machine translation (MT). A preliminary section on the post-editing process contains few details out of the ordinary; it might be noted that the agency/translator is required to determine whether the source text is at all suitable for MT, and that relevant specifications should exist. There are also requirements that the target text must fulfill; it can be noted that these requirements actually apply in equal measure to any translation, but they are not included in ISO 17100. Interestingly enough, the introduction notes that the rapid technological development in the MT field means that the standard is restricted to ‘that part of the process that begins upon the delivery of the MT output and the beginning (my italics) of the human process that is known as post-editing’.

As far as competencies and qualifications are concerned, it is worth noting that they are virtually identical to the corresponding text in ISO 17100 – that is, nothing specific to post-editing. However, there is also a sensible section on professional competence that includes requirements for “a basic understanding of common errors that an MT system makes” and “the knowledge and ability to establish whether editing MT output makes sense, in terms of time and effort estimations”.

Finally, there is a short chapter on the requirements of “full” post-editing, in addition to the general post-editing requirements. “Full” post-editing means that the resulting target text should not be distinguishable from a corresponding target text produced by a human professional translator without the assistence of MT.

ISO 5060

The standard gives guidance on the evaluation of human translation output, post-edited MT output, and unedited MT output. It focuses on an analytic translation evaluation approach using error types and penalty points configured to produce an error score and a quality rating. The focus is only on the human evaluation of translation output. However, anyone who has tried evaluation of this type knows that it is rather taxing.

A description of the standard is to be found at this OneWord site. And even more in the Multilingual magazine (you can have a free trial subscription), here.

Competencies and qualifications

Thankfully, ISO 17100 and 18587 set the same requirements for the translatorʼs competencies: Translation competence; linguistic and textual competence in source and target languages; competence in research, information acquisition and processing; cultural competence; technical competence; domain competence – all briefly described.

ISO 5060 requires the same competencies (even if sometimes slightly differently worded) as the two above but adds revision competence and evaluation competence.

ISO 20771 (legal translation) places far more and more detailed requirements. Thus, the translator must not only spend at least 5% of the working time on the cost of the work, but also participate in at least one training event a year, preferably be a member of a related professional organization, and document all training and education (how this can be done is described in an appendix).

ISO/TS 11669 deviates by simply specifying requirements for competences in source and target languages, but they are in fact qualifications. The same goes for its requirements on translation competences: they are also about qualifications.

There are three criteria for translation qualifications in ISO 17100 and 18587, of which at least one must be fulfilled: a degree in translation, a degree in any other field plus two years of professional experience, or five years of professional experience. The criteria of the legal standard are again far more far-reaching: six different ones, all of which must be met.

Informative appendix: Terminology

Much of the terminology is common between the standards. I would like to mention a few terms of specific interest here. (Remember that all terminology chapters are included in the free sample pages.) As you will see, the definitions in ISO/TS 11669 are often different from those in the other standards; it can be noted that in 11669 was published in 2012, whereas the others are 3-7 years later. Every Note is part of the standard as well.

• The following terms are found only in ISO/TS 11669:

A-language: native language, or language that is equivalent to a native language, into which the translator typically translates from his or her B-language and/or C-language

Note: The A-language is generally the language of education and daily life for a translator.

B-language: language, other than a translator’s native language, of which the translator has an excellent command and from which the translator typically translates into his or her A-language

C-language: language of which a translator has a complete understanding and from which the translator sometimes translates into his or her A-language

Note: A translator can have several C-languages.

overt translation: type of translation in which aspects of the source language and source culture are intentionally left visible

covert translation: type of translation intended to make the translation product appear as though it had been authored originally in the target language and target culture

requester: person or organization requesting a translation service from a TSP or language service provider [cf. client, customer below]

Note 1: The requester is usually the person or organization that asks for, and receives, the translation product on behalf of the end users, and that usually directly or indirectly determines the TSP’s compensation for rendering the translation service. In the case of government or non-profit organizations, pro-bono transactions, or in-house translation within a company, there is sometimes no monetary compensation for translation services.

Note 2: In the commercial sector, the requester is sometimes called the client or customer. These terms, however, are ambiguous and could refer to the end user. For this reason, requester is the preferred term.

• The following terms are common to all the standards:

locale: set of characteristics, information or conventions specific to the linguistic, cultural, technical and geographical conventions of a target audience

language register: variety of language used for a particular purpose or in a particular social or industrial domain

ISO 11669 has it slightly different: register; usage register: set of properties that is characteristic of a particular type of content, and which takes into account the nature of the relationship between the creator and audience, the subject treated and the degree of formality or familiarity of the content

translation service provider; TSP: language service provider that delivers translation services [ISO 11669: person or organization supplying a translation service]

Note: A TSP can be a translation company, a translation agency, a translation organization (profit, non-profit or governmental), a single freelance translator or post-editor, or an in-house translation department.

Note that the expression “language service provider” is used as if taken for granted, but without the common abbreviation LSP. However, in ISO/TS 11669 that term is also defined:

language service provider; LSP: person or organization that provides translation, interpreting and/or other language-related services such as transcription, terminology management or voice-overs

Note: The concepts of language service provider and TSP are connected by a generic relation, with language service provider being the generic concept and TSP the specific concept. TSPs generally provide only translation services, which can include revision or review. In some cases, language service providers provide mainly translation services but in many languages.

client; customer [not in ISO 11669]: person or organization that commissions a service from a TSP by formal agreement

Note: The client can be the person or organization requesting or purchasing the service and can be external or internal to the TSP’s organization.

reviser: person who revises translation output

• Furthermore:

revision: bilingual examination of target language content against source language content for its suitability for the agreed purpose [ISO 11669: bilingual editing of target content based on a comparison between the source content and the target content]

Note: The term bilingual editing is sometimes used as a synonym for revision.

review: monolingual examination of target language content for its suitability for the agreed purpose [ISO 11669: monolingual editing of target content with respect to the conventions of the subject field(s) to which the target content belongs]

Note: The term monolingual editing is sometimes used as a synonym for review.

proofread: examine the revised target language content and applying corrections before printing

correction: translation service action taken to correct an error in target language content or translation process or a nonconformity to a requirement of this International Standard when conformity has been claimed

Note: Corrections generally arise as a result of errors found when the translator is checking the target language content, when reported by a reviser or reviewer or proofreader or client, or during an internal or external audit of the implementation of this International Standard.

ISO 5060 contains a large number of terms related specifically to the evaluation of translations which are not found in the other standards.

(This post replaces the old one about the OpenAI plugin.) The documentation provided for the plugin OpenAI Provider for Trados is valid also for the built-in feature and is very informative, but you may need some more information about the account settings in OpenAI and Azure, i.e. the text under 1. Connections in that documentation.

Thus you first need to know how to create accounts.

OpenAI:

The link in the Settings window, Sign up for an OpenAI account, leads you to auth.openai.com/create-account, where you can create an account or log in to your already existing one. Creating a new account takes some time but will eventually land you at the OpenAI Platform (platform.openai.com), the Welcome page, where you will also get your first key. Furthermore, you need to purchase API credits, starting at $5 (lowest level), but you can also choose to buy credits later. After that, you will (finally) get to the starting page of your first project, giving access to everything you need.

However, this starting page

is not very relevant for your current needs. Instead, this top right menu is more relevant:

Via  SETTINGS you have access to your personal information (Profile), API keys, project information (Projects), Billing (where you can also enter payment information):

Also Usage (i.a. Total Spend). I leave it to you to explore the rest (there is such a lot!).

When you have an account and need to go back to this page, having logged out, you should go to platform.openai.com and log in.

Azure OpenAI:

The RWS Help page gives good information. In brief, you go to portal.azure.com to create an account. As with OpenAI above, the process is a bit lengthy. In the end, you will arrive at the #home page, where you can create (new) resources as well as view a list of the ones you have already created.

A resource, when you open it, gives access to (of particular interest here) endpoints and API keys, via Resource handling > Keys and endpoint. You can also view your Price level for the particular resource. And as with OpenAI, there is an enormous amount of other stuff on the various pages about which I know nothing.

(Updated March 10, 2025) The matter of language mapping is not something for which there is often a need, but just in case, I’ll give a brief description here. So:

• You might have a situation where one, or both, languages (usually the target language) does not have an “engine” in the MT Cloud, but you would like to use a language (or even pair) which is similar enough, language-wise, that to use it (them) could be of benefit.
• Or you do have a TM for exactly that pair, but it might be useful to use also a neighbouring language in an MT engine.
• Or even that you do have an MT engine from another provider than LW but, again, looking at another language would be beneficial.

The mapping table in the Language Weaver (LW) Provider makes it possible for you to assign an MT engine (in LW) for a different language than the one in the project (or, in an exceptional case, both languages).

Let’s say – to use an actual case – I have a translation from English to Luxembourgish, which latter language does not figure as an MT language in Language Weaver. However, since Luxembourgish is not too far away from German, using an MT engine for En > De might be useful. But I don’t want to go back and change the actual project languages. Here is where the language mapping comes in. This is how to do it.

I select, as MT/TM provider, Language Weaver Provider and then Language Weaver Cloud. Luxembourgish is not offered as a target language by the Language Weaver Cloud, and therefore the En > Lu pair causes it to tell me that the Target (language) is “Not set”. To remedy that, and still in the LW Cloud dialog, I open the mapping table by clicking Open Language Mapping:

Here, Language is the language I want to use LW for, and Region denotes the language variants; together they make up my language selection in Studio, such as “English (United Kingdom)”, or “Arabic (Algeria)” and are denoted by the Trados code. I need to find the proper language selection for the language that I want to assign a TM engine to.

Now, what I am after is the Language code to assign to my Language, because that is what actually decides which MT engine Language Weaver is going to use. In this case I want Luxembourgish to be mapped onto German, so I search for “lux” (in fact I only need to type “lu”; also note that the search filter looks at both Language and Region), and in the row for the Luxembourgish language (it only has one Region) I enter the Language code for German, “ger”, and click Apply. Getting back to the LW Cloud dialogue, I now see this:

The language pair is the same, but the target language for LW Cloud is now set to German (no longer “Not set”) – exactly as I wanted.

If the language to which I am mapping is a more obscure one for which I cannot easily find the language code in this table, I click the option Missing a language code? at the bottom of the table. Then I arrive at a Language Codes list: the available languages and their codes. (Actually practically all languages for which there is a language code is already in the Language Weaver Provider list; where one is missing it is probably not in the Language Codes list.)

If my project’s target language already has its own MT engine but I want to look at another (related) language, I can do such a mapping here. Let’s say I translate to Danish but would be helped by looking at an MT engine for Norwegian as the target. In the mapping table I select Danish – Danish and change the MT code “dan” into “nor”, click Apply, and get the desired result.

So – in principle simple although it takes a bit of text to explain it. My thanks to the ever-patient Paul Filkin for taking his time to clarify all my confusion.

Review of Jörg Porsiel (ed.): Maschinelle Übersetzung für Übersetzungsprofis. 384 pages. BDÜ Fachverlag 2020. €37. Order here (“Einkaufskorb” means “Shopping basket”).

Three years ago, the German translators’ organisation MDÜ published, via its publishing company BDÜ Fachverlag, the excellent machine translation primer “Machine Translation – What Language Professionals Need to Know” (reveiewed by myself here). Its original text was written in German; this follow-up is written in both English and German, and although its title is in German (easily translated into English: Machine Translation for Professional Translators), the fact is that about 57 percent of the text is in English! Still, some of the parts in German are of such importance that I wish they were made available to an even larger audience. (And one is written in a German which seems almost intentionally to confirm the image of German as an unusually difficult language, with long, convoluted sentences – the worst one being an entire paragraph of 9 lines, 83 words. All other contributions, however, are lucidly written.)

This is the book for everyone who wants to (a) get a comprehensive picture of the current situation in the domain of machine translation, and (b) delve deeper into some of the areas which are most important. In particular I would recommend reading the very first of the contributions, Patrick Bessler’s and Aljoscha Burchardt’s “Gute Qualität zum kleinen Preis? Wandel von Erwartungen und Prozessen im Kontext von Maschineller Übersetzung” (Good Quality at Low Cost? Changed Expectations and Processes in the Context of Machine Translation), because it gives such a complete and knowledgeable picture of the whole process, from client to translator/post-editor, stressing the need for knowledge on the part of the client and going into detail as concerns the new types of problems – in particular with the arrival of the neural MT – for both Language Service Providers (LSPs) and translators. (Examples are the new tasks which the LSPs must handle with regard to both clients and translators, the problem of assessing – in advance – the MT quality; and the new types of errors which must be handled.) Much of this – and more – is also touched upon in the foreword by the editor, Jörg Porsiel, but the in-depth coverage here, in only 12 pages, is admirable.

Today, as everyone knows, it’s the so-called neural variant which dominates MT. This has consequences for the handling of the MT suggestions – consequences which are discussed in many places in this book. But for the reader who is interested in the theories behind neural MT, there is a long presentation here (“Neural Machine Translation”, by Josef van Genabith) – 57 pages – with texts on information theory, mathematical expressions, and neural networks which may tax the reader’s concentration powers. However, there are also some parts of much more general interest, such as the detailed discussion of the differences between statistic and neural MT (pp. 73-74); also on human parity and research directions, where the discussion of translation for under-resourced languages is particularly important.

The future that MT brings

In particular I think van Genabith’s thoughts about the future are worth noting: “Going out on a limb, (N)MT will fundamentally change the work of human translators to (i) post-editing raw (N)MT translation outputs, (ii) certifying (post-edited or raw) translations and (iii) moving human translators much more into copy-editing and language and content quality control”. About that future there are further discussions. Donald DePalma writes about “Augmented Translation Intelligence”, where more or less “intelligent” functions will make possible a more extensive use of resources on the net (some interesting examples: “disambiguate words and phrases”, “deliver contextual information”, “suggest locale-specific content”) as well as the facilitation of the cooperation between colleagues. And his CSA colleague Arle Lommel makes (in “At human parity?”) some cutting remarks on the claims that NMT is (almost) on a par with “human” translation. He ends with some sensible suggestions as to what MT developers should concentrate on rather than pursuing the elusive target of “human parity”, namely improved quality estimation (see below), integration with speech technogies, connection with human translators, and simpler deployment.

Another look to the future is presented in “Machine Translation of Novels in the Age of Transformer”. Transformer is, according to the authors, “the state-of-the-art architecture in neural MT”. A project is presented where translations of 12 novels using different methodologies – one of which was Transformer – were evaluated. The authors do not claim any particular degree of “success”; only that Transformer is by far the best of the systems. They also suggest that training on segments longer than isolated sentences will lead to further improvements.

Yet another branch of future development is covered in “Neural Interactive Translation Prediction”; i.e. MT where basis for the MT suggestions are immediately updated. Unsurprisingly, this study indicates that such updating would be preferable to many translators; however, so far I know of only two providers (Lilt and CASMACAT, the one used here) offer that feature. (But the ModernMT service comes very close, with immediate updates of your uploaded TM, where matches take precedence over MT hits.)

When it comes to the future of post-editing work – i.e. editing of MT suggestions in a CAT tool, segment by segment; so-called PEMT – experienced post-editor Sara Grizzo is sceptical (in “Hat Post-Editing ausgedient?”; “Is Post-Editing a thing of the past?”):  this is demanding work which is to a large extent impopular among translators. She has come to the conclusion that, on the whole, PEMT makes sense above all for light post-editing (gisting). For more demanding translations, one should try to make use of MT in ways which are more palatable to the translator.

So what about post-editing itself?

PEMT is of course an important topic for this book, and it is covered in eight contributions. The aforementioned Sara Grizzo has two more contributions: one (“Post-Editing: ein Praxisleitfaden”) is a brief manual on the practise of post-editing. And in “Bezahlmodelle für Post-Editing” (“Payment models for Post-Editing”) she discusses the three main payment practices which are common today; one point being that none of them is really satisfactory. However, in the last contribution to the book, “Edit-Distance Based Compensation for Machine Translation”, Vincent Asmuth describes a variant of one of the models – EDC (for Edit-Distance Calculation) – which seems to take into account the work actually done by the post-editor, such as research and consideration of the MT suggestions, none of which is reflected in the resulting changes (if any) to the suggested translations. This is an interesting variant which could well be used as a starting point for discussion of this matter.

Another point raised by Grizzo is the importance of assessing in advance the amount of work needed for a post-editing job, and in particular the quality of the MT output. So far, only Memsource dares argue that they have a reliable function for this so-called Quality Estimation (as opposed to the Quality Control/Quality Assurance done on the final translation result), and it is briefly described, by Sara Szac and Heidi Depraetere, in “Quality Estimation”. They also describe a project called APE-QUEST, funded by the European Commission. They say that QE “should be used”; however, apart from referring to APE-QUEST – which I don’t believe is generally available – they do not provide any solutions.

Yet more on PEMT

Other articles on PEMT are, first, “DIN ISO 18587 in der Praxis” by Ilona Wallberg: an overview of the ISO standard, the title of which is “Translation services — Post-editing of machine translation output — Requirements”. Personally I am not sure of its importance, but since it is quite expensive (ca. EUR82) it is good to have it described in detail here.

Related to this contribution is “The post-editior’s skill set according to industry, trainers and linguists”, by Clara Ginovart and Antoni Oliver, which lists a number of skills fundamental to PEMT; the most important ones being “decision-making, error identification and respect of PE guidelines”.

“Post-edition – fit für die Praxis” (The Practice of Post-editing), by Uta Seewald-Heeg and Chuan Ding, is in some ways a companion text to Sara Grizzo’s shorter (and more easily read) “Praxisleitfaden”, already mentioned.

And a more psychologically-oriented approach to PEMT is taken by Jean Nitzke in “Problemlösungsstrategien beim Post-Editing in Verbindung mit psychologischen Aspekten” (Problem-solving Strategies in Post-Editing in Connection with Psychological Aspects). A question posed: Can a post-editor work with PEMT every day without the ability to concentrate and the motivation suffering? The perhaps obvious answer given here is that one should strive to work with a mixture of different tasks, and thereby develop methods and strategies for post-editing.

François Massion discusses PEMT from the viewpoint of an LSP (Language Service Provider) in “NMT im Einsatz bei einem Dienstleister” (NTM practiced by an LSP). It contains a section on optimization of post-editing (pp. 270-) which is certainly of general interest. And in a report on the use of terminology in training and customization of MT engines (“Terminologie in der neuronalen maschinellen Übersetzung” by Tom Winter and Daniel Zielinski) there is a discussion on the importance of terminology during translation which is well worth reading, in particular the detailed part on terminology errors in machine translations (pp. 216-).

As for the rest…

Other topics covered are the matter of confidentiality (two articles) and the use of controlled language (and while this discussion is certainly worth while, it is at least my experience that the LSP – not to mention the end-of-the-line translator/editor – extremely seldom has the opportunity to affect the source text in this manner).

It should also be mentioned that sprinkled in many of the contributions is the view that translation and post-editing are two very different tasks, and while a good post-editor is probably also a good translator, far from all translators find post-editing at all attractive.

If there is one perspective which I miss in this very rich book, however, it is the use of MT not for post-editing work – i.e. the use of MT is not requested by the client; it is simply used as an additional resource in a “normal” job. This is not the same task as PEMT! For one thing, you can choose among various MT engines; for another, it does not affect your pay. (But I must admit that the work itself is more or less similar to PEMT.)

Finally, I would strongly urge BDÜ to present this book all in English. While I am sure that most German-speaking readers have little problem with the English texts, I doubt that the reverse is true. And the book deserves a very wide readership. May I suggest to use the assistance of NMT?

There is also a brief glossary and presentations of the (30) contributors.

The MDÜ web site has a brief presentation of the book in German as well as sample pages – 18 of them, including the contents list.

Note: I had intended to provide a German version of this review as well, but in the end I refrained, since (a) my writing in German leaves a bit to be desired (even though I have no problem reading, and translating from, German), and (b) those German readers who are interested in this tome no doubt will have no problems reading this text in English.

This is a discussion held at the Studio Beta Group Forum. Since you have to be a member of that group to read it, and since it is quite interesting, I have obtained permission from the participants to publish it here.

Daniel Brockmann

Now that CU2 is out the door, I would love to hear from you on a specific topic. We are currently designing QA checks for the Online Editor environment, and “reinventing” them to some extent for that context. One question that came up was what typical default settings for QA checks are. Studio just has the forgotten check and nothing else enabled – which we believe is making its use a bit more difficult than if some other checks would already be available by default. So – against that background – can I ask you to reply here with the defaults you typically change? Obviously many of you also have specific RegEx checks etc. – maybe for those you can just say at a high level “I add my own regex checks” or so. A high-level list would be best.

Marco Rognoni 

I usually include the following:

Check for repeated words in target

Check that source and target end with the same punctuation

Check for multiple spaces

Claudio Nasso 

Regarding your QA checks question, these are my custom settings, compared to those already checked or unchecked by default:

• Segment verification > Source and target are identical
• Segments to Exclude > Exclude exact matches
• Segments to Exclude > Exclude repetitions
• Segments to Exclude > Exclude locked segment
• Inconsistencies > Check for inconsistent translations
• Inconsistencies > Check for repeated words in target
• Inconsistencies > Check for unedited fuzzy matches
• Punctuation > Check that source and target end with the same punctuation
• Punctuation > Check for unintentional spaces before (applies to Italian, in my case)
• Punctuation > Check for multiple spaces
• Punctuation > Check for multiple dots
• Punctuation > Check for multiple dots > Ignore ellipsis dots (…)
• Punctuation > Check for extra space at the end of target segment
• Punctuation > Check brackets
• Numbers > Check numbers
• Numbers > Check times
• Numbers > Check dates
• Numbers > Check measurements
• Trademark check > Check trademarks characters
• Length limitations > Check length limitation (only when necessary)
• Tag verifier > Ignore formatting tags (in this case I uncheck it)
• Verification settings > Ignore locked segments
• Verification settings > Enable recognition of two-letters terms
• Number verifier > Number verifier settings > Exclude tag text
• Number verifier > Number verifier settings > All source thousands separators > Period (applies to Italian, in my case)
• Number verifier > Number verifier settings > All decimal separators > Comma (applies to Italian, in my case)

Marco Rognoni 

Hi Claudio,

That’s a lot of QA checks! 🙂

Personally my experience is that by adding so many checks you always get a lot of errors, and it takes more time to verify each of them in Studio rather than manually check them during review/proofreading stages before delivery.

Of course each of us has a personal way of working, so I totally understand that you may prefer to have all those checks in place.

This shows that Daniel’s question is very interesting, and most likely each reply will be different based on the established method of every single linguist.

Claudio Nasso 

Hi Marco,

you are right, enabling all my proposed verification items may generate lot of errors/warnings/notes, but this is true only when the review/editing stages of a translated project have been carried out in an inadequate way.

When the reviewing/proofreading stages have been correctly carried out, the number of “errors/warnings/notes” will be much less, and they will further help us to spot those we have forgotten.

Moreover, after having set general custom QA checks, pairing them to the proper “signal” (I mean “Error”, “Warning” or “Note”), we have an option to show just the desired “signal”, or to disable some of them before running the “Verify” function on a particular project.

But, as you have pointed out, the choice of custom QA settings is tied to specific projects/requirements, and I agree with you that Daniel’s question is interesting because it will spot various working methods adopted by each colleague.

Tuomas Kostiainen 

Generally, I use the following checks:

• Segment verification > Check for forgotten and empty translations
• Segments to Exclude > Exclude PerfectMatch units
• Segments to Exclude > Exclude locked segment
• Inconsistencies > Check for inconsistent translations [Ignore tags and case]
• Inconsistencies > Check for repeated words in target [Ignore numbers and case]
• Punctuation > Check for unintentional spaces before [:!?;]
• Punctuation > Check for multiple spaces
• Punctuation > Check for multiple dots > Ignore ellipsis dots (…)
• Punctuation > Check for extra space at the end of target segment
• Regular Expressions > I use my own
• Trademark check > Check trademark characters
• (Length limitations > Check length limitation [only when necessary])
• Tag verifier > All 5 tag checks AND Ignore formatting tags

(Copied and modifed from Claudio’s list — thank you!)

Frank Drefs 

We use the following settings:

Segment verification > Source and target are identical

• Segments to Exclude > All deselected
• Inconsistencies > Check for inconsistent translations (Ignore tags + Ignore case selected)
• Inconsistencies > Check for repeated words in target (Ignore case selected)
• Inconsistencies > Check for unedited fuzzy matches
• Punctuation > Check for multiple dots
• Punctuation > Check for multiple dots > Ignore ellipsis dots (…)
• Tag verifier > All checks selected
• Tag verifier > Ignore formatting tags

Claudia Alvis 

• Segment verification > Check for forgotten and empty translations
• Inconsistencies > Check for inconsistent translations [Ignore tags and case]
• Inconsistencies > Check for repeated words in target [Ignore numbers]
• Inconsistencies > Check for unedited fuzzy matches [All segments]
• Punctuation [All checked]
• Numbers [None checked]
• Trademark check > Check trademarks characters
• Length limitations > Check length limitation (only when necessary)
• Tag verifier [Tags added, Deleted, Ghost tags]
• Terminology verifier > Check for possible non-usage of target terms [min. match value 85%]
• Terminology verifier > Check for terms which may have been set as forbidden
• Terminology verifier > Ignore locked segments

Note: This is a revised version of a text previously published at the eMpTy Pages blog under the heading “The Data Security Issues Around Public MT – A Translator Perspective”, with an extensive introduction by blog editor Kirti Vashee and some reader comments. This version is slightly updated.

Some time ago there were a couple of posts on this site discussing data security risks with machine translation (MT), notably by Kirti Vashee and by Christine Bruckner. Since they covered a lot of ground and might have created some confusion as to what security options are offered, I believe it may be useful to take a closer look with a more narrow perspective, mainly from the professional translator’s point of view. And although the starting point is the plugin applications for SDL Trados Studio, I know that most of these plugins are available also for other CAT tools.

About half a year ago, there was an uproar about Statoil’s discovery that some confidential material had become publicly available due to the fact that it had been translated with the help of a site called translate.com (not to be confused with translated.net, the site of the popular MT provider MyMemory). The story was reported in several places; this report gives good coverage.

Does this mean that all, or at least some, machine translation runs the risk of compromising the material being translated? Not necessarily – what happened to Statoil was the result of trying to get something for nothing; i.e. a free translation. The same thing happens when you use the free services of Google Translate and Microsoft’s Bing. Frequently quoted terms of use for those services state, for instance, that “you give Google a worldwide license to use, host, store, reproduce – – – such content”, and (for Bing): “When you share Your Content with other people, you understand that they may be able to, on a worldwide basis, use, save, record, reproduce – – – Your Content without compensating you”. This  should indeed be offputting to professional translators but should not be cited to scare them from using services for which those terms are not applicable.

The principle is this: If you use a free service, you can be almost certain that your text will be used to “improve the translation services provided”; i.e. parts of it may be shown to other users of the same service if they happen to feed the service with similar source segments. However, the terms of use of Google’s and Microsoft’s paid services – Google Cloud Translate API and Microsoft Text Translator API – are totally different from the free services. Not only can you select not to send back your finalized translations (i.e. update the provider’s data with your own translations); it is in fact not possible – at least not if you use Trados Studio – to do so.

Google and Microsoft are the big providers of MT services, but there are a number of others as well (MyMemory, DeepL, Lilt, Kantan, Systran, SDL Language Cloud…). In essence, the same principle applies to most of them. So let us have a closer look at how the paid services differ from the free.

Google’s and Microsoft’s paid services

Google states, as a reply to the question Will Google share the text I translate with others: “We will not make the content of the text that you translate available to the public, or share it with anyone else, except as necessary to provide the Translation API service. For example, sometimes we may need to use a third-party vendor to help us provide some aspect of our services, such as storage or transmission of data. We won’t share the text that you translate with any other parties, or make it public, for any other purpose.”

And here is the reply to the question after that, Will the text I send for translation, the translation itself, or other information about translation requests be stored on Google servers? If so, how long and where is the information kept?: “When you send Google text for translation, we must store that text for a short period of time in order to perform the translation and return the results to you. The stored text is typically deleted in a few hours, although occasionally we will retain it for longer while we perform debugging and other testing. Google also temporarily logs some metadata about translation requests (such as the time the request was received and the size of the request) to improve our service and combat abuse. For security and reliability, we distribute data storage across many machines in different locations.”

For Microsoft Text Translator API the information is more straightforward, on their “API and Hub: Confidentiality” page: “Microsoft does not share the data you submit for translation with anybody.” And on the “No-Trace” page: “Customer data submitted for translation through the Microsoft Translator Text API and the text translation features in Microsoft Office products are not written to persistent storage. There will be no record of the submitted text, or portion thereof, in any Microsoft data center. The text will not be used for training purposes either. – Note: Known previously as the “no trace option”, all traffic using the Microsoft Translator Text API (free or paid tiers) through any Azure subscription is now “no trace” by design. The previous requirement to have a minimum of 250 million characters per month to enable No-Trace is no longer applicable. In addition, the ability for Microsoft technical support to investigate any Translator Text API issues under your subscription is eliminated.”

Other major players

As for DeepL, there is the same difference between free and paid services. For the former, it is stated – on their “Privacy Policy DeepL” page, under Texts and translations – DeepL Translator (free) – that “If you use our translation service, you transfer all texts you would like to transfer to our servers. This is required for us to perform the translation and to provide you with our service. We store your texts and the translation for a limited period of time in order to train and improve our translation algorithm. If you make corrections to our suggested translations, these corrections will also be transferred to our server in order to check the correction for accuracy and, if necessary, to update the translated text in accordance with your changes. We also store your corrections for a limited period of time in order to train and improve our translation algorithm.”

To the paid service, the following applies (stated on the same page but under Texts and translations – DeepL Pro): “When using DeepL Pro, the texts you submit and their translations are never stored, and are used only insofar as it is necessary to create the translation. When using DeepL Pro, we don’t use your texts to improve the quality of our services.” And interestingly enough, DeepL seems to consider their services to fulfil the requirements stipulated – currently as well as in the coming legislation – by the EU Commission (see below).

Lilt is a bit different in that it is free of charge, yet applies strict Data Security principles: “Your work is under your control. Translation suggestions are generated by Lilt using a combination of our parallel text and your personal translation resources. When you upload a translation memory or translate a document, those translations are only associated with your account. Translation memories can be shared across your projects, but they are not shared with other users or third parties.”

MyMemory – a very popular service which in fact is also free of charge, even though they use the paid services of Google, Microsoft and DeepL (but you cannot select the order in which those are used, nor can you opt out from using them at all) – uses also its own translation archives as well as offering the use of the translator’s private TMs. Your own TM material cannot be accessed by any other user, and as for MyMemory’s own archive, this is what they say, under Service Terms and Conditions of Use:

“We will not share, sell or transfer ’Personal Data’ to third parties without users’ express consent. We will not use ’Private Contributions’ to provide translation memory matches to other MyMemory’s users and we will not publish these contributions on MyMemory’s public archives. The contributions to the archive, whether they are ’Public Data’ or ’Private Data’, are collected, processed and used by Translated to create statistics, set up new services and improve existing ones.” One question here is of course what is implied by “improve” existing services. But MyMemory tells me that it means training their machine translation models, and that source segments are never used for this.

And this is what the SDL Language Cloud privacy policy says: “SDL will take reasonable efforts to safeguard your information from unauthorized access. – Source material will not be disclosed to third parties. Your term dictionaries are for your personal use only and are not shared with other users using SDL Language Cloud. – SDL may provide access to your information if SDL plc believes in good faith that disclosure is reasonably necessary to (1) comply with any applicable law, regulation or legal process, (2) detect or prevent fraud, and (3) address security or technical issues.”

Is this the whole truth?

Most of these terms of services are unambiguous, even Microsoft’s. But Google’s leaves room for interpretation – sometimes they “may need to use a third-party vendor to help us provide some aspect of [their] services”, and occasionally they “will retain [the text] for longer while [they] perform debugging and other testing”. The statement from MyMemory about improving existing services also raises questions, but I am told that this means training their machine translation models, and that source segments are never used for this. However, since MyMemory also utilizes Google Cloud Translate API (and you don’t know when), you need to take the same care with both MyMemory and Google.

There is also the problem with companies such as Google and Microsoft that you cannot get them to reply to questions if you want clarifications. And it is very difficult to verify the security provided, so that the “trust but verify” principle is all but impossible to implement (and not only with Google and Microsoft).

Note, however, that there are plugins for at least the major CAT tools that offer possibilities to anonymize (mask) data in the source text that you send to the Google and Microsoft paid services, which provides further security. This is also to some extent built into the MyMemory service.

But even if you never send back your translated target segments, what about the source data that you feed into the paid services? Are they deleted, or are they stored so that another user might hit upon them even if they are not connected to translated (target) text?

Yes and no. They are generally stored, but – also generally – in server logs, inaccessible to users and only kept for analysis purposes, mainly statistical. Cf. the statement from MyMemory.

My conclusion, therefore, is that as long as you do not return your own translations to the MT provider, and you use a paid service (or Lilt), and you anonymize any sensitive data, you should be safe. Of course, your client may forbid you to use such services anyway. If so, you can still use MT but offline; see below.

What about the European Union?

Then there is the particular case of translating for the European Union, and furthermore the provisions in the General Data Protection Regulation (GDPR), to enter into force on 25 May 2018. As for EU translations, the European Commission uses the following clause in their Tender specifications:

”Contractors intending to use web-based tools or any other web-based service (e.g. cloud computing) to execute the /framework contract/ must ensure full compliance with the terms of this call for tenders when using such services. In particular, the provisions on confidentiality must be respected throughout any web-based process and the Union’s intellectual and industrial property rights must be safeguarded at all times.” The commission considers the scope of this clause to be very broad, covering also the use of web-based translation tools.

A consequence of this is that translators are instructed not to use “open translation services” (beggars definition, does it not?) because of the risk of losing control over the contents. Instead, the Commission has its own MT-system, e-Translation. On the other hand, it seems possible that the DG Translation is not be quite up-to-date as concerns the current terms of service – quoted above – of Google Cloud Translate API and Microsoft Text Translation API, and if so, there may be a slight possibility that they might change their policy with regard to those services. But for now, the rule is that before a contractor uses web-based tools for a EU translation assignment, an authorisation to do so must be obtained (and so far, no such requests have been made).

As for the GDPR, it concerns mainly the protection of personal data, which may be a lesser problem generally for translators (at least if you don’t handle texts such as medical records, legal cases, etc.). In the words of Kamocki & Stauch on p. 72 of Machine Translation, “The user should generally avoid online MT services where he wishes to have information translated that concerns a third party (or is not sure whether it does or not)”. If you do handle personal data, you should forget about MT since the new regulation requires you to have a contract with the data processor (i.e. the MT service provider), and I doubt that for instance Google or Microsoft will be bothered.

Offline services and beyond

There are a number of MT programs intended for use offline (as plugins in CAT tools), which of course provides the best possible security (apart from the fact that transfer back and forth via email always constitutes a theoretical risk, which some clients try to eliminate by using specialized transfer sites). The drawback – apart from the fact that being limited to your own TMs – is that they tend to be pretty expensive to purchase.

The ones that I have found (based on investigations of plugins for SDL Trados Studio) are, primarily, Slate Desktop translation provider, Transistent API Connector, and Tayou Machine Translation Plugin. I should add that so far in this article I have only looked at MT providers which are based on providers of statistical machine translation or its further development, neural machine translation. But it seems that one offline contender which for some language combinations (involving English) also offers pretty good “services” is the rule-based PROMT Master 18.

However, in conclusion I would say that if we take the privacy statements from the MT providers at face value – and I do believe we can, even when we cannot verify them – then for most purposes the paid translation services mentioned above should be safe to use, particularly if you take care not to pass back your own translations. But still I think both translators and their clients would do well to study the risks described and advice given by Don DePalma in this article. Its topic is free MT, but any translation service provider who wants to be honest in the relationship with the clients, while taking advantage of even paid MT, would do well to study it.

Note 1: This is a revised version of a text previously published at the eMpTy Pages blog under the heading “Post-editing” – what does it really mean?”. This version is more up-to-date (and slightly enlarged), but the blog post is followed by several interesting comments not included here.

Note 2: This new version, published on 2 April, is a very much revised version of the one previously published here.

You might wonder in what way editing of hits in a CAT tool’s TM is different from editing of ”hits” in an MT engine. Because if there was not a clear difference there would not be any reason to invent a particular term for the latter.

But the term ”post-editing” is established since the 1980s, so there should be something to it.[1] And the way I see the difference is this: Certainly for many years, Déjà Vu – in particular – but also memoQ and perhaps also other CAT tools have cleverly put together TM fragments into more or less complete target segment translations, but they can almost never pre-translate whole documents, something which MT can do. It is true that the MT-translated target text might be almost totally useless, but the point is that a client might come to you and say: Here is a machine translated document; could you go through it and produce a useful result? Or: Here is a French document; could you run it in this MT motor and edit the target segments into good German? The expectation, of course, being that the use of MT will make the translation cost less.

The difference lies not so much in the job itself – even if many people say that post-editing of MT-translated texts is rather much different from the ”ususal” translation in a CAT tool with one or more TMs, or without one – as the fact that an MT produces a complete translation – usable or not – of  (in theory at least) every piece of source text.

Post-editing also means that the client requests use of an MT motor (or has already used it). If I, in a normal job, use MT and even produce the whole translation by editing MT-translated segments, that’s a different case (and one which does not concern anyone but me, provided that confidentiality is not compromised in any way). Another factor to consider is whether the translation task concerns a pre-translated document or the translator translates the text segment by segment in the usual way but using the suggestions from an assigned MT. I’ll discuss that later in this article.

The matter of quality

In a post-editing job, a level of quality is also specified – the client wants a translation which is good enough for its purposes but does not want to pay for one that is “unnecessarily” good. Therefore the following quality levels have been defined, in the ISO standard 18587:2017, Translation services – Post-editing of machine translation output – Requirements and other documents:

1. Light post-editing (also called “gisting”): The final text is understandable and correct as to content, but the editor need not – and should not – strive for a text much better than that; s/he should use as much as possible of the unedited MT version.
2. Full post-editing: The result, according to some definitions, should be ”indistinguishable from human output” (in the words of ISO 18587), or ”publishable”. But there are are conflicting views on this: some sources say that stylistic perfection is not expected and that clients actually do not expect the result to be comparable to “human” translation. ”Do not worry too much about style, standards of textuality” and ”Quality expectations: medium”.[2] And: ”Texts that are post-edited should not strive for linguistic perfection; instead, the goal should be linguistic adequacy.”[3]

Looking past the definitions in the standard and instead using definitions of what I perceive as practice, I would say that there are in fact three levels of post-editing MT output: At the top there is the result ”indistinguishable from human output”; i.e. it is impossible to tell whether MT has been used or not. Slightly below that, there is the ”full” post-editing: correct in all regards but perhaps not top-level stylistically. And then there is the ”ligth” level: useable for understanding but not more (not much fun to read).

Of course these categories are only points on a continuous scale; it is difficult to objectively test that a PEMT text fulfils the criteria of one or the other. (Is the light version really not above the target level? Is the full version really up to the requirements? Has the client specified what type of full version is required?).

There are some interesting research results as to the efforts involved, insights which may be of help to the would-be editor. Thus it seems that editing medium quality MT (at all levels) takes more effort than editing poor ones – it is cognitively more demanding than discarding and rewriting the text. Also the effort needed to detect an error and decide how to correct it may be greater than the rewriting itself; and reordering words and correcting mistranslated words takes the longest time of all.

There is also interesting research which shows that a translation’s “fluency” – in the eyes of the post-editor – trumps “correctness”[4], and that a translation which contains a preferred wording but is in fact incorrect will pass, while a correct translation will often be edited to include a preferred wording.[5]

An additional aspect is that all jobs involving “light” quality is likely to be avoided by most translators since it goes against the grain of everything a translator finds joy in doing, i.e. the best job possible. Experience also shows that all the many decisions that have to be made regarding which changes need to be made and which not often take so much time that the total effort with “light” quality editing is not much less than that with “full” (or even ”best”) quality.

Pre-translation or interactive editing?

Then there is the question of whether the job involves a pre-translated document or segment by segment “interactive” translation in a CAT tool with the aid of an MT motor. I have read many articles and presentations and even dissertations on post-editing, and strangely, very few of them have made this distinction. In fact, in many of them it seems as if the authors are primarily thinking of the latter (and the vast majority of the research is done on interactive work). Furthermore, most descriptions or definitions of “post-editing” do not seem to take into account any such distinction. All the more reason, then, to welcome the following definition in ISO 17100:2015, Translation services – Requirements for translation services:

post-edit

edit and correct machine translation output

Note: This definition means that the post-editor will edit output automatically generated by a machine translation engine. It does not refer to a situation where a translator sees and uses a suggestion from a machine translation engine within a CAT (computer-aided translation) tool.

And yet… in ISO 18587, Translation services – Post-editing of machine translation output – Requirements, we are back in the uncertain state: the above note has been removed, and there are no clues as to whether the standard makes any difference between the two ways of producing the target text to be edited.

This may be reasonable in view of the fact that the requirements on the “post-editor” arguably are the same in both cases (and it seems that was the rationale for the decision to delete the note). And it may not matter to the quality of the work performed or the results achieved. But it matters a great deal to the translator doing the work. Basically, there are three possible job scenarios:

1. The job consists of editing (“post-editing”) a complete document which has been machine-translated; the source document is attached, and the client defines the desired level of quality. The editor (usually an experienced translator) can reasonably well assess the quality of the translation and based on that make an offer. The offer should take into account any necessary adaptation of the source and target texts for handling in a CAT tool.
2. The job is very much like a normal translation in a CAT tool except that instead of, or in addition to, an accompanying TM the translator is assigned an MT engine by the client (usually a translation agency). Here, too, a level of quality is defined. The agency may have a template (similar to the “Trados grid”) for payment, or simply a standard level related to the payment for “normal” translation – normally 60%. But usually it is not possible for the translator to assess in advance the time required (partly because there is still no method for judging in advance the quality of an MT engine).
3. The same as B, but the payment is based on a post-analysis[6] of the edited file and depends on how much use has been made of the MT (and, as the case may be, the TM) suggestions. As in B, it is not possible to assess the time required, nor in this scenario the final payment. Also, s/he may not know how the post-analysis is made, in which case the final compensation will be based on trust. (And, of course, if this method of basing payment on a post-assessment of the job done becomes accepted, one can easily foresee it being applied as well to traditional jobs using CAT tools in combination with TMs, without machine translation.)

In addition to this, there are differences between scenarios A and B/C in how the work is done. For instance, in A you can use Find & replace to make changes in all target segments; not so in B/C (unless you start by pre-translating the whole text using MT) – but there you may have some assistance by various other functions offered by the CAT tool and also by using Regular expressions (regex). And if it’s a big job, it might be worthwile, in scenario A, to create a TM based on the texts and then redo the translation using that TM plus any suitable CAT tool features (and regex). And so on.

What about the future?

I was given an interesting view of the development of translation work is given by Arle Lommel, senior analyst at CSA Research and an expert in the field. It goes like this:

A major shift right now is that post-editing is being replaced by “augmented translation.” In this view, language professionals don’t correct MT, but instead use it as a resource alongside TM and terminology. This means that buyers will increasingly just look for translation, rather than distinguishing between machine and human translation. They will just buy “translation” and the expectation will be that MT will be used if it makes sense. The MT component of this approach is already visible in tools from Lilt, SDL, and others, but we’re still in the early days of this change.

Here, “light” post-editing is not even in the picure; I am not aware of today’s demand but I can imagine that this type of work in future will be of interest mainly for larger companies, which then probably can handle it internally.

If mr Lommel is correct, it probably means that we can stop using the “post-editing” misnomer as we do today – editing is editing, regardless of whether the suggestion presented in the CAT tool interface comes from a TM or an MT engine. (This erasing of boundaries is well described by Sharon O’Brien.[7]) It should be reserved only for the very specific case of scenario A. This view is taken in, among others, the contributions by a post-editor educator and an experienced post-editor in the recently published Machine Translation – What Language Professionals Need to Know[8],[9].

My own view of the future is as follows (without any figures at all to back it up):

As neural MT – and “adaptive” statistical MT – produces better and better results, and this becomes known (as it will be) by clients such as big companies and translation agencies, the situation described by mr Lommel will also mean that prices will be forced further down as productivity rises. But this may not be all doom and gloom, or as this quotation states:

The translators of tomorrow will have more in common with skilled engineers than with today’s linguists, who operate in a craft-driven model. The will wiels an array of technologies that amplify their ability and the will be able to focus on those aspects that require human intelligence and understanding, while leaving routine tasks to MT.[10]

(Or, as someone put it, “machine translation will only replace those who translate like machines”.)

Thus it seems that “post-editing” as a service is likely to disappear. But the task of editing MT output will remain, although looking more and more like the task of editing/reviewing the output of a fellow translator. This probably also means that the need for special “post-editors”, as well as a corresponding special training, will disappear – although it will always remain a fact that some translators will avoid the job of editing while others enjoy it. And certainly editing/reviewing merits a place in the education of translators – many of the shortcomings of post-editors found in the research are obviously not primarily caused by the fact that the text-to-be-edited comes from MT.

And while we await that time, very far away I believe, when the only need for human translators will be for translating fiction, we translators of today should strive to make the best possible use of the situation where MT, even if not required by the client, is a resource to be used, or not, as any (other) TM. It is here and will not go away even if some people would wish it to. Or put another way:

[NMT] represents a major breakthrough that [Langugage Service Providers] and their clients should actively investigate. Those that wait will find themselves at a disadvantage.[11]

References:

[1] Maybe a clue is to be found in this statement: “Post-editing should not be confused with pre-editing.” Although how such a confusion might arise I don’t understand. (From Trusted Translations, https://www.trustedtranslations.com/translation-services/post-editing.asp.)

[2] O’Brien, Sharon, Roturier, Johann, and de Almeida, Giselle (2009): Post-Editing MT Output. CNGL. http://www.mt-archive.info/MTS-2009-OBrien-ppt.pdf

[3] Hansen-Schirra, Silvia, Schaeffer, Moritz, and Nitke, Jean (2017). Post-editing: strategies, quality, efficiency. In Porsiel (ed.): Machine Translation. Berlin: BDÜ Fachverlag.

[4] Martindale, Marianna J. & Carpuat, Marine (2018): Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT. https://arxiv.org/pdf/1802.06041.pdf

[5] Koponen, Maarit (2013): This translation is not too bad: An analysis of post-editor choices in a machine translation post-editing tas. In Proceedings of MT Summit XIV Workshop on Post-editing Technology and Practice. https://pdfs.semanticscholar.org/b659/ec47ebf3d05fe38ada7ed45d3afd54434d74.pdf

[6] See for instance Memsource’s ”Post-editing Analysis”, https://help.memsource.com/hc/en-us/articles/115003942912-Post-editing-Analysis

[7] O’Brien, Sharon (2016): Post-Editing and CAT. In: 2016 48 EST Newsletter. https://issuu.com/est.newsletter/docs/2016_48-est

[8] Hansen-Schirra, Schaeffer, Nitke, ibid.

[9] Grizzo, Sara (2017): Working as a post-editor: a field report. In Porsiel (ed.): Machine Translation. Berlin: BDÜ Fachverlag.

[10] Lommel, Burchardt and Macketanz (2018): Will neural technology drive MT into the mainstream? In MultiLingual, January 2018. http://dig.multilingual.com/2018-01/index.html?page=0

[11] Lommel, Burchardt and Macketanz, ibid.

If sometimes you are stuck with a pdf file without recourse to the source, and the layout is complicated with perhaps images inserted in the text, various columns, and whatnot – then your solution is probably called Infix.

Infix is a program with two main functions: (1) It allows you to edit any pdf file. (2) It allows you to create an xliff file for translation in Studio (or other CAT tools);  the translation (in xliff format) can then be imported into Infix where a translated pdf can be created (and edited). Note that what you get is thus a pdf – while you can get the same text also in rtf format (see below), that document is completely without a layout and thus of very limited use, i.e. no better than what Studio can produce.

Here is what you do. (For background and a training video, you should also read & watch Paul Filkin’s blog post Handling PDFs… is there a best way?)

Download, registration and installation

First, go to the Infix home page (www.iceni.com) and take a look, for your information. Then select Infix PDF Editor and Try It For Free!, which will download the installation zip file. Install it.

After installation, you should also click Buy from €8.99 on the http://www.iceni.com/infix.htm page. When you do this, it does not mean you have to buy; you arrive at a page where you can (a) see the different purchase options, and also register for the free trial: scroll to somewhere around the middle of this page and click the Try It for Free button and go on from there.

Note: The difference between the free trial and the subscription is that with the former, you can edit not more than 50 final pdf pages in the Infix PDF Editor; after that it’s 50 cents per page. And it is unlikely that the resulting page(s) don’t require at least some editing. So do your calculations and make your choice.

The work process

1.      Open Infix.

2.      Open the pdf file you want to translate.

3.      Select Translate > Export as XLIFF.

This process requires you to log in (with the details you created/gave during registration) and also to select source and target languages as well as file name. Furthermore, your file organiser will open, so that you can check if the xlf file has been created. This is just for your information; close it if you like.

The exported document will be opened in Infix and you can see if it looks promising (with really complicated pages, you may see that you will still have some work to do after everything is done, but believe me, that’s nothing compared to all other ways of handling the same material).

Note: During this process, a box opens telling you that the document is being uploaded to TransPDF.com. That page is where everything is being done, and if you want to, you can follow the processes there, as in this image. As for how to open that page, see the end of this post.

Now you’re ready to translate:

4.      Open Studio.

5.      Select Translate Single Document, open the xml file you just created and select suitable TM(s) or machine translation or whatever. If appropriate, do a pre-translation batch task.

6.      When your translation is finalised (or when you just want to check how it looks), save it in xlf format (Shift+F12). Normally it’s OK to overwrite the original xlf file (you will be asked).

Note: All the following steps can be performed whether the translation is complete or only partly done.

7.      In Infix, select Translate > Import translated XLIFF.

8.      Browse to the xliff translation you just created and then select the Import button.

Preview or go to Final PDF?

When the import is done, you get to choose whether to view a preview of the result. You can do this as an intermediate step, or you can skip it and download the final pdf version. In both cases, you get to choose between Normal view, Compare Horizontal and Compare Vertical, the comparisons being between the source document and the preview/final version. The preview will be watermarked (“TransPDF.com”), but that will be removed in the final translation. Another difference is that the preview is read-only, whereas the final version can be edited (see below).

The preview also contains a starting page listing translation data as well as any font problems and their resolutions (such as “Futura-Bold -> Alegreya Sans Black) and instructions on how to deal with possible problems. If you skip this stage, you can still get this font report page from the Infix site – see below.

9.      Download the final pdf: Select Translate > Download Final PDF. Select the translated xml and, if necessary, rename it so that the result is kept separate from the previous translation xml file. As with the preview, you can select to open it alone or together with the original pdf. If you open for comparison but decide you only want to see/work with resulting pdf alone, just close the comparison and open the result (with Ctrl+O as usual).

Together with the opened file, you may get a window listing possible problems, such as this:

For a close look at a problem, select it and click View. You may experiment with the Text Fitting option, but you can also use the editing tools on top of the Infix window. Paul Filkin gives some instructive examples of such editing in his video, at 10:25. The editing is a bit tricky, but there is a comprehensive guide to be accessed via the program’s Help menu; also on-line tutorials.

You can also have the translation in rtf format (without any kind of page layout). For that, you need to go to your own TransPDF site: Go to the registration/sign-in page at http://www.iceni.com/transpdf.htm and sign in. This page opens:

As you see, you have here some of the options on the Translate menu, plus the option of downloading the final rtf, which sometimes might be useful for editing purposes. Also, once you have translated the file you can use this page instead of the Infix interface. One difference is that for the editing of the final pdf, you do need Infix.

This text replaces the corresponding section in the manual; it has been removed in order to save space there but also because its “competitor”, AutoHotkey seems to be more popular. It is also easier to use; on the other hand, I think PhraseExpress offers a large number of useful functions well worth exploring.

Start at the PhraseExpress feature list and look round; then download and try it.
The application, when started, is found in the Taskbar’s system tray. Right-clicking it will produce this menu:

You open the PhraseExpress window by selecting Edit phrases:

This is where you manage your autotext entries, phrases, hotkeys, etc.; we’ll get back to that. To familiarise yourself with the Help is a good idea, and you can also do that without installing PhraseExpress: it is here.

Note 1: The help text often refers to the Settings option, which you will find on the Tools menu.

Note 2: The PhraseExpress functions do not work if you have this window open, so after any action performed in it: minimise it or close it.

Text replacement (with AutoText)

1. Select the phrase you want PhraseExpress to insert when you type its “abbreviation”.
2. Press Ctrl+Alt+C. This dialog box opens:

3. Enter a suitable Autotext abbreviation. (The Hotkey option is mainly intended for the execution of macros; see below.)
4. Press OK.

When you type the abbreviation and the selected delimiter, the entry in the Description field will be inserted instead.

AutoCorrect

There is no specific auto-correction function; just as in Word, any misspelled word listed as an “abbreviation” will be replaced by its corresponding (correctly spelled) Description. Of course, for this you need a list corresponding to the lists provided with Word, and you need to import it into PhraseExpress. Depending on language, there are two alternatives:

• Use one of the lists offered by PhraseExpress: En, De, Nl, Fr, Es, Po, or It
• Import your Word AutoCorrect entries

Import AutoCorrect entries provided by PE

1. Open the PhraseExpress window (right-click the tray icon and select Edit phrases).
2. In the Phrases and Folders pane, open the File menu and select Download additional contents. The PhraseExpress site opens with the Free PhraseExpress Add-Ons window.
3. Click a suitable AutoCorrect file and save it.
4. In the Phrases and Folders pane, select New folder.
5. Open the File menu, select Import and then PhraseExpress Phrase File.
6. Locate the file you just downloaded (a .pxp file) and open it. Answer Yes to the message window that opens (to avoid duplicate entries).

The result (for German) looks like this (the corresponding English material is already provided by default):

Import Word AutoCorrect entries

1. Open the PhraseExpress window (right-click the tray icon and select Edit phrases).
2. In the Phrases and Folders pane, select New folder.
3. Open the File menu, select Import and then MS Word AutoCorrect entries. Answer Yes to the message window that opens (to avoid duplicate entries).
4. A new folder, Imported MS Word AutoCorrect entries, is created, with the imported content.

Should it happen that the import consists of the English list instead of your target language, you need to extract the AutoCorrect entries for that language – see the instructions in the AutoHotkey section below.

Input correction entries with TypoLearn

When you make a manual correction of a typing error, PhraseExpress registers that as an AutoCorrect entry for future use. (It seems you have make the same correction three times for PhraseExpress to pick it up.) This applies to single word entries if you have ended them with a space character, then deleted that space with backspace, corrected the word and then again ended it with a space. Entries are stored in the Word Corrections folder.

Text suggestions (AutoComplete)

Here is a potentially very useful function: PhraseExpress can recognise words, phrases and spelling correction which have occurred repeatedly and stores them for use exactly in the way Studio uses AutoSuggest. It may be a good idea to take a look at the settings for this (Tools > Settings > AutoSuggest).

Import an external phrase file

You can import phrase files of your own (e.g. to provide text suggestions for AutoComplete). See the Help file, the section headed Importing an External Bitmap or Text File.

Enable/disable a phrase folder

Obviously, you can have phrase folders with contents in different languages. To avoid possibly confusing AutoCorrections etc., you can disable irrelevant folders: right-click the folder and select Enable Autotext/Hotkeys so that the checkmark disappears.

Clipboard manager

PhraseExpress has a “clipboard cache” function which saves a number of clipboard contents. By pressing Ctrl+Alt+V, you can select them in a popup menu (and by right-clicking a content you get further options).

Macros

There is an enormous amount of actions you can perform using the macro functions in PhraseExpress. Most of them may not be very useful in Studio, however.

When you open a partly translated file to continue translating it, you may encounter the error message “Dependency file not found” with the question “Would you like to browse for this [i.e. the original] file?”.

What to do:

If you have the original source file, the simplest solution is to answer Yes to the question in the error message and locate the source file. (Normally the appropriate folder will be automatically opened; if not, you need to locate it. Once it is open, go to the field to the right at the bottom and change the file type to All files; then the source file should be listed and can be opened. If not, see the second option below.) But if you are working on a project package, you will normally not have any source files included. Here are two ways to proceed:

• Close the project in Studio. Go to the project’s TM file (where all your translations so far are stored) and re-name it (or if you want to be really safe, copy it to another location). Open the original .sdlproj file again (i.e. re-create the project from scratch). Then change the project settings to use your “old” TM instead of the newly created one, and run the batch task Pre-translate Files. (Whatever you do, do not just re-open the project package without safeguarding your TM, since the TM which is generated will overwrite the existing TM with the same name and you will have lost all your work.)

• Another method in both cases (project package or not) is to skip the source file matter and answer No to the question in the error message. You can then continue translating as usual, but you cannot Save Target As, Finalize, Generate Target Translations or Preview. What you can do, however, is make sure that the TM you produce is complete; i.e. does not contain any unconfirmed or un-translated segments.

Once you have done this, you can start from scratch using the TM you have just produced. Or, in case of a project package, follow the procedure described above.

There are other solutions, mostly to do with restoring the dependency files or repairing the .sdlxliff files, but to me they seem unnecessary complicated and not completely reliable.

Why this happens:

According to the Knowledge Base, a dependency file is created “when the original file is too large to be embedded in the .sdlxliff file”, and a ‘dependency file’ is then created which contains a link to the original file. The dependency file is stored as a temporary (.temp) file. However, some computer tune-up/diagnostics software will delete all .temp files unless they are instructed not to (you need to find out for yourself how to do that). It could also happen that the Windows hibernation function is the cause, in which case that particular energy option needs to be disabled.

Furthermore, you can adjust the Studio settings which control the file size leading to the creation of dependency files. Go to Files > Options > File Types > SDLXLIFF – General and move the ruler under “Embedding” to its maximum (100 MB). Why is the default value 20 MB, and will this change have any negative effects? I don’t know. (Thanks to Walter Blaser for pointing to this solution.)

There is an entry in the RWS Community dealing with this problem; it is rather old but it may still be of help. Or you can go to the RWS Community and “Search the Knowledgebase and Community” for suggested solutions to this problem. There are a lot…