machine translation bias removal tool
DEMO
Announcement

Introducing the Fairslator API

Like what Fairslator does? Want to have something similar in your own application? There's an API for that!

I am pleased to announce the launch of the Fairslator API today: a machine-readable interface which software developers can use to include Fairslator’s functionality in their own applications (that’s why “API” stands for “Application Programming Interface”).

The Fairslator API is a service on the web (technically: a REST API, if these acronyms mean anything to you) where you can submit a piece of text and, within a few milliseconds, get it back rewritten in a different gender or a different form of address. Fairslator’s website uses the very same API too – and now I am making it available to other developers who might want to use it to build something similar, or who simply need to rewrite some texts.

In the rest of this article I will summarize what the API does, in what kinds of scenarios it might be useful to you, and how to start using it.

What does the API do?

The Fairslator API does two things: gender rewriting and form-of-address rewriting. But what exactly are those two things?

Let’s look at gender rewriting first. In many languages, words that refer to people by occupation – such as pilot, doctor, bus driver and student – come in gender pairs: there is one word for a male person having that occupation and another word for a female person having it. The Fairslator API can find them in a text and change one into the other. It does this in a way which keeps the text grammatically correct, so that any adjectives, determiners and co-referring pronouns are changed too.

Example (French: I am a good student.):

  • Je suis un bon étudiant. (male)
    →   Je suis une bonne étudiante. (female)

In addition to this, the Fairslator API can rewrite gender-specific texts into gender-neutral neoforms, which is handy when you’re referring to a mixed-gender group of people and want to avoid the male default.

Example (German: All visitors must register.):

  • Alle Besucher müssen sich registrieren. (male default)
    →   Alle Besucher:innen müssen sich registrieren. (gender-neutral)

The second thing the Fairslator API can do for you is form-of-address rewriting. While English only has one form of address – the second-person pronoun you – many other languages have several, depending on whether you’re talking to one person or many, and whether you’re addressing them formally or informally. The form of address you choose affects not only pronouns but also other words in the text such as verbs. The Fairslator API can rewrite texts from one form of address into another.

Example (German: Do you know where you are?):

  • Wissen Sie, wo Sie sind? (formal)
    →   Weißt du, wo du bist? (informal singular)
    →   Wisst ihr, wo ihr seid? (informal plural)

Who needs this API?

You can do all of these things on Fairslator’s own website, of course. But if you need to have rewriting features integrated into something you’re building yourself, then you need the API. In what scenarios might that be the case?

In translation management systems. If you have a platform in your company where human users are post-editing machine translation, you can give them more control over how gender and forms of address are translated. Machine translation engines produce translations that are often biased in these things (for example tending to always translate doctor as male doctor) but the Fairslator API can help you to quickly and even “invisibly” rewrite those biased translations as needed.

In conversational machine translation. If you’re using machine translation to translate texts of a conversational nature – such as film subtitles, or a real-time chat – you probably know a great deal about the people involved: their genders, which level of formality is appropriate, and so on. You can use this information – along with the Fairslator API – to rewrite the machine translation output in real time as needed.

In personalized user interfaces. When an app or a website communicates with human users, you might want to customize the on-screen texts based on what you know about the people involved: whether they are male or female, whether they prefer to be addressed formally or informally, which other people the texts refer to, and so on. The Fairslator API can help you do these rewrites dynamically and in real time instead of having to manually hard-code every possible option beforehand.

How is the API available?

I have decided to make the API available through RapidAPI, a popular marketplace where publishers and consumers of APIs meet one another. So, to start using the API, go to Fairslator’s listing on RapidAPI, sign up for an account there if you haven’t got one yet, and start exploring. You can sign up for the Basic plan which lets you make a certain number of API calls per day for free, or the Pro plan which allows you to use the API more extensively for an affordable fee.

Fairslator API’s listing on RapidAPI

I’ll be curious to hear what people are using the API for, so feel free to get in touch and tell me how the API is working out for you. I will always welcome constructive feedback and feature suggestions.

Note

Finally, a house-keeping clarification. This API is work in progress and, at this point, supports a narrower range of languages than Fairslator’s website. Currently, the API can only rewrite texts in German and French, and translations from English into German and from English into French. More languages and language pairs will be added to the API later.

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
Download
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.
| Machine translation
Google Translate versus gender bias
How does Google Translate handle gender-ambiguous input? With difficulty.
| 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.
| 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’?
| 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’?
| 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’.
| 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

coming up icon wider October 2024 — We will be talking about bias in machine translation at a Translating Europe Workshop organised by the European Commission in Prague as part of Jeronýmovy dny, a series of public lectures and seminars on translation and interpreting.
icon September 2024 — We are presenting a half-day tutorial on bias in machine translation at this year's biennial conference of AMTA, the Association for Machine Translation in the Americas.
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 machinetranslation.com 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 2022Slator.com, 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.