Analyzing Gender Representation in Multilingual Models
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
YARE-GAN: Yet Another Resting State EEG-GAN
VANPY: Voice Analysis Framework
Graph Contrastive Learning for Connectome Classification
OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
BN-AuthProf: Benchmarking Machine Learning for Bangla Author Profiling on Social Media Texts
GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.