They, Them, Theirs: Rewriting with Gender-Neutral English
This work addresses the need for inclusive natural language systems to support diverse users, though it is incremental as it focuses on a specific rewriting task.
The paper tackled the problem of promoting gender inclusion in English by developing a model to rewrite text using singular 'they' with a word error rate under 1%, without requiring human-labeled data.
Responsible development of technology involves applications being inclusive of the diverse set of users they hope to support. An important part of this is understanding the many ways to refer to a person and being able to fluently change between the different forms as needed. We perform a case study on the singular they, a common way to promote gender inclusion in English. We define a re-writing task, create an evaluation benchmark, and show how a model can be trained to produce gender-neutral English with <1% word error rate with no human-labeled data. We discuss the practical applications and ethical considerations of the task, providing direction for future work into inclusive natural language systems.