Papers › Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings

Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings

11 Mar 2021COLING 2022 10arXiv:2103.06459archive 2025-07-28

Linlin Liu, Thien Hai Nguyen, Shafiq Joty, Lidong Bing, Luo Si

Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel framework to align contextual embeddings at the sense level by leveraging cross-lingual signal from bilingual dictionaries only. We operationalize our framework by first proposing a novel sense-aware cross entropy loss to model word senses explicitly. The monolingual ELMo and BERT models pretrained with our sense-aware cross entropy loss demonstrate significant performance improvement for word sense disambiguation tasks. We then propose a sense alignment objective on top of the sense-aware cross entropy loss for cross-lingual model pretraining, and pretrain cross-lingual models for several language pairs (English to German/Spanish/Japanese/Chinese). Compared with the best baseline results, our cross-lingual models achieve 0.52%, 2.09% and 1.29% average performance improvements on zero-shot cross-lingual NER, sentiment classification and XNLI tasks, respectively.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ntunlp/multisense_embedding_alignment officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Lingual NER Cross-Lingual Word Embeddings NER Sentiment Analysis Sentiment Classification Word Embeddings Word Sense Disambiguation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BERT BiLSTM Dense Connections Dropout ELMo LSTM Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Sigmoid Activation Softmax Tanh Activation Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections