paper-with-me

홈 › Papers

Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study

2020-09-29 · Findings of the Association for Computational Linguistics 2020 · Saurabh Kulshreshtha, José Luis Redondo-García, Ching-Yun Chang

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.

📄 PDF Abstract BibTeX arXiv:2009.14304

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual Transferslot-fillingSlot FillingZero-Shot Cross-Lingual Transfer

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
mBERT mBERT
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings

2025-12-29 · Wen G. Gong arxiv

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

2020-04-11 · EMNLP 2020 11 · Uma Roy, Noah Constant, Rami Al-Rfou, Aditya Barua 외

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 TranslationRetrievalTranslation

Identifying Necessary Elements for BERT's Multilinguality

2020-05-01 · Philipp Dufter, Hinrich Schütze

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

2020-11-01 · EMNLP 2020 11 · Philipp Dufter, Hinrich Sch{\"u}tze

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

2025-07-29 · Jens-Joris Decorte, Matthias De Lange, Jeroen Van Hautte arxiv

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