Analyzing Gender Representation in Multilingual Models

PROCEEDINGS OF THE 7TH WORKSHOP ON REPRESENTATION LEARNING FOR NLP(2022)

引用 0|浏览42
暂无评分
摘要
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 representation 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.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络