Zero-shot Cross-lingual Transfer is Under-specified Optimization
원문 초록
Pretrained multilingual encoders enable zero-shot cross-lingual transfer, but often produce unreliable models that exhibit high performance variance on the target language. We postulate that this high variance results from zero-shot cross-lingual transfer solving an under-specified optimization problem. We show that any linear-interpolated model between the source language monolingual model and source + target bilingual model has equally low source language generalization error, yet the target language generalization error reduces smoothly and linearly as we move from the monolingual to bilingual model, suggesting that the model struggles to identify good solutions for both source and target languages using the source language alone. Additionally, we show that zero-shot solution lies in non-flat region of target language error generalization surface, causing the high variance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Cross-Dialect Information Retrieval: Information Access in Low-Resource and High-Variance Languages
Table Question Answering for Low-resourced Indic Languages
Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing
PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment
News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation
Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer
토론
이 논문과 연결된 포럼 글이 아직 없습니다.