machine translation bias removal tool
Status update

What’s new with Fairslator #3

Fairslator is now available as a browser plug-in, and other news.

It’s been six months since my last status update on Fairslator, so another one is long overdue. A lot has happened in those six months, so let’s dive right in.

A screenshot of Bias Shield

Fairslator has joined forces with the DeBiasByUs project (which is collecting and analyzing examples of gender-biased translations) and together we have developed a web browser extension called Bias Shield. Bias Shield adds bias-handling features to Google Translate and DeepL. Every time you visit one of these websites, you will see a small panel at the bottom of your screen where you can disambiguate and debias your translations the same way you do in Fairslator but without having to visit Fairslator’s website. There is also a button to report the translation as gender-biased to DeBiasByUs, to suggest a bias-free alternative, and if the translation has been reported before, Bias Shield will tell you about it and will show you the bias-free alternatives that other people have suggested. You can install Bias Shield in your Chrome and in your Firefox.

A screenshot of CAPE·MT

That’s not the only new product launched recently. February saw the launch of CAPE·MT, a parallel project to Fairslator intended for professional translators. CAPE·MT (the abbreviation stands for “computer-aided post-editing of machine translation”) contains the same functionality as Fairslator but organized a little differently to meet the needs of professional translators who are post-editing the output of machine translation. Machine translation post-editing (MTPE) is a relatively new job description in the translation industry and, sadly, it has a rather mixed reputation for being repetitive, boring and uncreative: you’re making the same kinds of edits over and over again, such as changing genders around or changing between formal and informal forms of address. CAPE·MT makes this less painful by pregenerating these edits automatically and suggesting them to the human post-editor, who can then accept or reject them with one click. I’ve built the CAPE·MT web app as a prototype to demonstrate this new proposed workflow, and I am competing with it in this year’s LocWorld Process Innovation Challenge. The preliminary round of this competition is on next week and it’s online, so if this technology interests you, do come along to watch and support me!

A photo of a conference

What else? Towards the end of last year I presented Fairslator at the Translating and the Computer conference in Luxembourg, and in February this year published a long interview with me where we discussed everything there was to discuss about (not only) gender bias in machine translation: Creating an Inclusive AI Future: The Importance of Non-Binary Representation. I did already mention that I’m competing in LocWorld’s Process Innovation Challenge, and if I get qualified for the final round I’ll get a chance to present CAPE·MT at LocWorld, a major conference and trade show for the translation and localization industry, which is taking place in Malmö, Sweden in June. As if that wasn’t enough, the annual conference of the European Association for Machine Translation is taking place in Tampere, Finland this year (also in June) and, as part of this conference, the First International Workshop on Gender-Inclusive Translation Technologies is being held. I’m on the scientific committee for this workshop and I hope to present some of my own work there too. My friends from the DeBiasByUs project will also be there, so if you only have time to visit one event this year, visit this one!

Some computer code

Finally, what’s happening with Fairslator itself? I haven’t had a chance to launch any new functionality or new language pairs since the last update. Instead, I have been secretly working behind the scenes on a complete rewrite of Fairslator’s back-end. The current version of the code that powers Fairslator is the result of explorative programming which, frankly, contains a lot of hard-to-debug spaghetti code. I decided to clean up all of that, to remove some external dependencies which were making it difficult for me to reach the high levels of reliability and accuracy I aim for, and generally to put the project on a sustainably long-term footing. I hope to launch the new back-end this summer and to start offering it as a subscription-based API for anyone who wants to integrate Fairslator-like functionality (and CAPE·MT-like functionality) into their own software tools. So, watch this space for exciting new announcements soon!

Contact the author

What next?

Read more about bias and ambiguity in machine translation.
Cover page
We need to talk about bias
in machine translation
The Fairslator whitepaper
Sign up for my very low-traffic mailing list. I'll keep you updated on what's new with Fairslator and what's happening with bias in machine translation generally.
Your address is safe here. I will only use it to send you infrequent updates about Fairslator. I will not give or sell it to anyone. You can ask me to be taken off the list at any time.

Faislator blog

| Infographic
How gender rewriting works in machine translation
This is how Fairslator deals with gender-biased translations.
| Announcement
Introducing the Fairslator API
Like what Fairslator does? Want to have something similar in your own application? There's an API for that!
| Machine translation
Google Translate versus gender bias
How does Google Translate handle gender-ambiguous input? With difficulty.
| Status update
What’s new with Fairslator #2
Fairslator now speaks French, and other news.
| Gendergerechte Sprache
Kann man das Gendern automatisieren?
Überall Gendersternchen verstreuen und fertig? Von wegen. Geschlechtergerecht zu texten, das braucht vor allem Kreativität.
| Oh là là
Three reasons why you shouldn’t use machine translation for French
But if you must, at least run it through Fairslator.
| Ó Bhéarla go Gaeilge
Tusa, sibhse agus an meaisínaistriúchán ó Bhéarla
Tugaimis droim láimhe leis an mhíthuiscint nach bhfuil ach aon aistriúchán amháin ar gach rud.
| Status update
What’s new with Fairslator #1
A new language pair, some new publications, plus what's in the pipeline.
| Machine translation
Finally, an Irish translation app that knows the difference between ‘tú’ and ‘sibh’
It asks you how you want to translate ‘you’.
| Forms of address
Why machine translation has a problem with ‘you’
This innocent-looking English pronoun is surprisingly difficult to translate into other languages.
| Male and female
10 things you should know about gender bias in machine translation
Machine translation is getting better all the time, but the problem of gender bias remains. Read these ten questions and answers if you want to understand all about it.
| Machine translation in Czech
Finally, a translation app that knows the difference between Czech ‘ty’ and ‘vy’!
Wouldn’t it be nice if machine translation asked how you want to translate ‘you’?
| Gender bias in machine translation
Gender versus Czech
In Czech we don’t say ‘I am happy’, we say ‘I as a man am happy’ or ‘I as a woman am happy’.
| German machine translation
Finally, a translation app that knows the difference between German ‘du’ and ‘Sie’!
Wouldn’t it be nice if machine translation asked how you want to translate ‘you’?
| Strojový překlad
Představ si, že jseš stroj, který překládá
Proč se překladače nikdy neptají, jak to myslíme?
| Maschinelle Übersetzung
Stell dir vor, du bist DeepL
Warum fragt der Übersetzer eigentlich nicht, was ich meine?

Fairslator timeline

icon December 2023 — Fairslator presented a workshop on bias in machine translation at the European Commission's Directorate-General for Translation, attended by translation-related staff from all EU institutions.
icon November 2023 — Fairslator went to Translating and the Computer, an annual conference on translation technology in Luxembourg, to present its brand new API.
icon November 2023 — We were talking about gender bias, gender rewriting and Fairslator at the EAFT Summit in Barcelona where we also launched an exciting spin-off project there: Genderbase, a multilingual database of gender-sensitive terminology.
November 2023 — English–French language pair added to the Fairslator API.
July 2023 — The Fairslator API was launched. Explore the API or read the announcent: Introducing the Fairslator API »
icon February 2023 — We spoke to about bias in machine translation, about Fairslator, and about our vision for “human-assisted machine translation”. Read the interview here: Creating an Inclusive AI Future: The Importance of Non-Binary Representation »
icon October 2022 — We presented Fairslator at the Translating and the Computer (TC44) conference, Europe's main annual event for computer-aided translation, in Luxembourg. Proceedings from this conference are here, the paper that describes Fairslator starts on page 90. Read our impressions from TC44 in this thread on Twitter and Mastodon.
icon September 2022 — In her article Error sources in machine translation: How the algorithm reproduces unwanted gender roles (German: Fehlerquellen der maschinellen Übersetzung: Wie der Algorithmus ungewollte Rollenbilder reproduziert), Jasmin Nesbigall of oneword GmbH talks about bias in machine translation and recommends Fairslator as a step towards more gender fairness.
icon September 2022 — Fairslator was presented at the Text, Speech and Dialogue (TSD) conference in Brno.
icon August 2022Translations in London are talking about Fairslator in their blog post Overcoming gender bias in MT. They think the technology behind Fairslator could be useful in the translation industry for faster post-editing of machine-translated texts.
August 2022 — A fourth language pair released: English → French.
icon July 2022 — Germany's Goethe-Institut interviewed us for the website of their project Artificially Correct. Read the interview in German: Wenn die Maschine den Menschen fragt or in English: When the machine asks the human, or see this short video on Twitter.
icon May, a website for the translation industry, asked us for a guest post and of course we didn't say no. Read What You Need to Know About Bias in Machine Translation »
April 2022 — A third language pair added: English → Irish.
February 2022 — Fairslator launched with two language pairs: English → German, English → Czech.