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

By Hila Gonen, Yova Kementchedjhieva, Yoav Goldberg. 2019

26 citations recorded by the source corpus.

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 results in 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.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Evaluating Gender Bias in Hindi-English Machine Translation (2021, background): “Gonen et al. (2019) worked on addressing the problem with such inan-imate nouns as well and attempted to neutralize the grammatical gender signal of these words during training by lemmatizing the context words and changing the gender of these words.”
Intrinsic Bias Metrics Do Not Correlate with Application Bias (2020, background): “It is important to take a language with pervasive gender-marking (Spanish) into account, as previous work has shown that grammatical gender-marking has a strong effect on gender bias (McCurdy and Serbetci, 2017; Gonen et al., 2019; Zhou et al., 2019).”