Towards zero-shot cross-lingual named entity disambiguation

作者:

Highlights:

• Novel zero-shot cross-lingual Named Entity Disambiguation approach.

• Robust system that does not require native prior probabilities.

• Purpose-built multilingual method outperforms generic models such as XLM-R.

• English is not necessarily the most effective training language for zero-shot.

• New dataset for Basque/English, which facilitates further research.

摘要

•Novel zero-shot cross-lingual Named Entity Disambiguation approach.•Robust system that does not require native prior probabilities.•Purpose-built multilingual method outperforms generic models such as XLM-R.•English is not necessarily the most effective training language for zero-shot.•New dataset for Basque/English, which facilitates further research.

论文关键词:Cross-lingual named entity disambiguation,Cross-lingual entity linking,Zero-shot learning,Transfer learning,Pre-trained language models,Low-resource languages

论文评审过程:Received 22 February 2021, Revised 29 June 2021, Accepted 30 June 2021, Available online 9 July 2021, Version of Record 20 July 2021.

论文官网地址:https://doi.org/10.1016/j.eswa.2021.115542