The Fairslator API takes a text in a natural language and changes it into a different gender or form of address. The same API powers the Fairlslator web app, a popular tool for removing biases from machine translation.

What is gender rewriting?

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)

What is form-of-address rewriting

Where 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 the Fairslator API?

The Fairslator API can help you add gender and form-of-address rewriting features into your own applications. When might you need that?

In translation management systems. If you have a platform in your enterprise where human users are post-editing machine translation, you can give them more control over how gender and forms of address are translated. Machine translator 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.

What next?

You are now ready to start exploring the Fairslator API. I have prepared a few handy tutorials so feel free to delve into those. I’ve also invested a lot of effort into getting the API endpoints properly documented, hopefully you’ll find that useful. And I will always welcome constructive feedback and feature suggestions here in the Discussions section or by e-mail: michmech@lexiconista.com

Language coverage

The Fairslator API canrewrite texts in German and French, and translations from English into German and from English into German. More languages will be added in due time.