Analyzing Gender Representation in Multilingual Models

Hila Gonen, Shauli Ravfogel, Yoav Goldberg


Abstract
Multilingual language models were shown to allow for nontrivial transfer across scripts and languages. In this work, we study the structure of the internal representations that enable this transfer. We focus on the representations of gender distinctions as a practical case study, and examine the extent to which the gender concept is encoded in shared subspaces across different languages. Our analysis shows that gender representations consist of several prominent components that are shared across languages, alongside language-specific components. The existence of language-independent and language-specific components provides an explanation for an intriguing empirical observation we make”:” while gender classification transfers well across languages, interventions for gender removal trained on a single language do not transfer easily to others.
Anthology ID:
2022.repl4nlp-1.8
Volume:
Proceedings of the 7th Workshop on Representation Learning for NLP
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Spandana Gella, He He, Bodhisattwa Prasad Majumder, Burcu Can, Eleonora Giunchiglia, Samuel Cahyawijaya, Sewon Min, Maximilian Mozes, Xiang Lorraine Li, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Laura Rimell, Chris Dyer
Venue:
RepL4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
67–77
Language:
URL:
https://aclanthology.org/2022.repl4nlp-1.8
DOI:
10.18653/v1/2022.repl4nlp-1.8
Bibkey:
Cite (ACL):
Hila Gonen, Shauli Ravfogel, and Yoav Goldberg. 2022. Analyzing Gender Representation in Multilingual Models. In Proceedings of the 7th Workshop on Representation Learning for NLP, pages 67–77, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Analyzing Gender Representation in Multilingual Models (Gonen et al., RepL4NLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.repl4nlp-1.8.pdf
Video:
 https://aclanthology.org/2022.repl4nlp-1.8.mp4
Code
 gonenhila/multilingual_gender