machine translation bias removal tool
Oh là là

Three reasons why you shouldn’t use machine translation for French

But if you must, at least run it through Fairslator.

You know how it is: you want to say something in French but you’re not quite sure how, so you rush to a machine translation tool such as Google Translate or DeepL.

Yes, machine translators have become really good in recent years, especially in high-profile language pairs such as English-French. But don’t let that lull you into a false sense of security. No matter how good the AI gets, there will always be occasions when the machine has understood something differently – and therefore translated it differently – from how you meant it.

This article will show you three examples of that, explain why they happen, and tell you how Fairslator can keep you safe from those traps.

1. What do you mean by ‘you’?

You probably know that French has two words you ‘you’: tu refers to one person and vous refers to several people. Vous can also refer to one person if you’re addressing him or her formally, while tu is informal.

You know this, but does Google Translate know it? Not really. Ask Google Translate (or any other machine translator) to translate ‘I like you’ and it will pick tu or vous more or less arbitrarily. What if it picks tu but you wanted to say this sentence to a group of people?

To prevent that from happening, the trick is not to use Google Translate directly but to use it through Fairslator. Fairslator is a tool which obtains translations from an external machine translator and then puts them through an ambiguity detection filter. When it detects that more than one translation is possible – like in this case with ‘you’ – it warns you about it and gives you a choice: do you want to to translate ‘you’ as single person or multiple people, as formal or informal? Depending on what you answer Fairslator re-inflects the translation.

Fairslator re-inflecting ‘I like you’ depending on what you mean by ‘you.

2. Student, director and other gender-specific nouns

Enough about ‘you’, let’s talk about other people. French is one of the many European languages that have gender-specific words for occupations. Where English has ‘student’ French has étudiant for male student and étudiante for female student. Where English has ‘director’ French has directeur for male director and directrice for female director.

This is another stumbling block for machine translators. If you ask them to translate a sentence with one of these words in it, such as ‘I am the new director’, it will probably translate that with the male version, directeur. The machine is biased in favour of male directors because it has seen more male than female directors in its training data. But what if you’re a woman? Then announcing to people that you are their new directeur (instead of directrice) is going to make you sound a bit silly.

The trick is, again, not to use machine translation directly but to go through Fairslator. Fairslator will detect that there are two gender-specific translations for ‘director’ and ask you which one you want.

Fairslator helping you with gender-specific translation.

3. Happy as a man, happy as a woman

And it gets worse: the same gender-specificity affects adjectives too, if they are positioned after the verb être (‘to be’). This means that even a simple sentence like ‘I am happy’ has two possible translations for ‘happy’, depending on whether the person that ‘I’ refers to is male or female: je suis heureux if male, je suis heureuse if female.

Again, machine translators usually jump to a conclusion and assume that the person under ‘I’ must be male. To prevent that from happening, use Fairslator instead.

Fairslator asking you your gender so it can translate ‘I am happy’ correctly.

En conclusion...

These have been just three examples of situations where machine translators often fail to deliver the correct translation. They fail because they jump to conclusions too quickly: they assume they now know better than you what you mean by certain words. Fairslator is a plug-in for many popular machine translators which reverse-engineers these assumptions and hands control back to you, the human user.

So, tell all your French-speaking friends about Fairslator – but don’t forget to use the correct translation for ‘you’!

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!
| Status update
What’s new with Fairslator #3
Fairslator is now available as a browser plug-in, and other news.
| 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.
| 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.