How Does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?

Hila Gonen, Yova Kementchedjhieva, Yoav Goldberg


Abstract
Many natural languages assign grammatical gender also to inanimate nouns in the language. In such languages, words that relate to the gender-marked nouns are inflected to agree with the noun’s gender. We show that this affects the word representations of inanimate nouns, resulting in nouns with the same gender being closer to each other than nouns with different gender. While “embedding debiasing” methods fail to remove the effect, we demonstrate that a careful application of methods that neutralize grammatical gender signals from the words’ context when training word embeddings is effective in removing it. Fixing the grammatical gender bias yields a positive effect on the quality of the resulting word embeddings, both in monolingual and cross-lingual settings. We note that successfully removing gender signals, while achievable, is not trivial to do and that a language-specific morphological analyzer, together with careful usage of it, are essential for achieving good results.
Anthology ID:
K19-1043
Volume:
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Mohit Bansal, Aline Villavicencio
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
463–471
Language:
URL:
https://aclanthology.org/K19-1043
DOI:
10.18653/v1/K19-1043
Bibkey:
Cite (ACL):
Hila Gonen, Yova Kementchedjhieva, and Yoav Goldberg. 2019. How Does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 463–471, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
How Does Grammatical Gender Affect Noun Representations in Gender-Marking Languages? (Gonen et al., CoNLL 2019)
Copy Citation:
PDF:
https://aclanthology.org/K19-1043.pdf
Attachment:
 K19-1043.Attachment.pdf
Code
 gonenhila/grammatical_gender