Papers with unsupervised cross-lingual word embeddings

2 papers
A Graph-based Coarse-to-fine Method for Unsupervised Bilingual Lexicon Induction (2020.acl-main)

Copied to clipboard

Challenge: Recent methods for bilingual lexicon induction are based on unsupervised cross-lingual word embeddings . previous methods only use word-level information, which is limited and inaccurate .
Approach: They propose a graph-based approach to induce bilingual lexicons in a coarse-to-fine way . they use word cliques from graphs and aligned clique-level words to find initial translation solution .
Outcome: The proposed method improves the performance of bilingual lexicon induction compared with previous methods.
A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity (P19-1)

Copied to clipboard

Challenge: Cross-lingual word embeddings encode the meaning of words from different languages into a shared low-dimensional space.
Approach: They show that modularity can be used to improve unsupervised word embeddings . they show that it is useful for low-resource languages where one often has few bilingual pairs .
Outcome: The proposed model improves unsupervised cross-lingual word embeddings on distant language pairs in low-resource settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations