Cross-lingual embeddings with auxiliary topic models

作者：

Highlights：

• A novel way to learn effective topical cross-lingual embeddings.

• Using bilingual topic models to enrich a seed bilingual lexicon.

• Unsupervised models perform worse than their supervised competitors.

摘要

•A novel way to learn effective topical cross-lingual embeddings.•Using bilingual topic models to enrich a seed bilingual lexicon.•Unsupervised models perform worse than their supervised competitors.

论文关键词：Cross-lingual embeddings,Topical models,Word embedding models,Projection-based methods,Seed dictionaries

论文评审过程：Received 15 May 2020, Revised 22 July 2021, Accepted 2 November 2021, Available online 14 November 2021, Version of Record 18 November 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116194