← Search

Lina Conti

1 accepted papers

2023

Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models

EMNLP 2023short main

Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards exploring the less researched topic of how neural models discover linguistic properties of words, such as gender, as wel…

Cited by 0SourceScholar