Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study
Multilingual BERT (mBERT) has shown reasonable capability for zero-shot cross-lingual transfer when fine-tuned on downstream tasks. Since mBERT is not pre-trained with explicit cross-lingual supervision, transfer performance can further be improved by aligning mBERT with cross-lingual signal. Prior work proposes several approaches to align contextualised embeddings. In this paper we analyse how different forms of cross-lingual supervision and various alignment methods influence the transfer capability of mBERT in zero-shot setting. Specifically, we compare parallel corpora vs. dictionary-based supervision and rotational vs. fine-tuning based alignment methods. We evaluate the performance of different alignment methodologies across eight languages on two tasks: Name Entity Recognition and Semantic Slot Filling. In addition, we propose a novel normalisation method which consistently improves the performance of rotation-based alignment including a notable 3% F1 improvement for distant and typologically dissimilar languages. Importantly we identify the biases of the alignment methods to the type of task and proximity to the transfer language. We also find that supervision from parallel corpus is generally superior to dictionary alignments.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Lingual Transferslot-fillingSlot FillingZero-Shot Cross-Lingual TransferMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings
With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-drive…
LAReQA: Language-agnostic answer retrieval from a multilingual pool
We present LAReQA, a challenging new benchmark for language-agnostic answer retrieval from a multilingual candidate pool. Unlike previous cross-lingual tasks, LAReQA tests for "strong" cross-lingual alignment, requiring …
Machine TranslationRetrievalTranslationIdentifying Necessary Elements for BERT's Multilinguality
It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during …
Identifying Elements Essential for BERT's Multilinguality
It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during …
Multilingual JobBERT for Cross-Lingual Job Title Matching
We introduce JobBERT-V3, a contrastive learning-based model for cross-lingual job title matching. Building on the state-of-the-art monolingual JobBERT-V2, our approach extends support to English, German, Spanish, and Chi…
Contrastive Learning