Multi-sense embeddings through a word sense disambiguation process
作者：
Highlights：
• Unsupervised word sense disambiguation technique for diverse NLP tasks.
• Word embeddings combining sense disambiguation, improving its vector representation.
• Synset embedding models can help to leverage the disambiguation of polysemous words.
• Multi-sense embedding models provide better representation than single-sense ones.
• Recurrent synset-embedding models can improve the quality of word representations.
摘要
•Unsupervised word sense disambiguation technique for diverse NLP tasks.•Word embeddings combining sense disambiguation, improving its vector representation.•Synset embedding models can help to leverage the disambiguation of polysemous words.•Multi-sense embedding models provide better representation than single-sense ones.•Recurrent synset-embedding models can improve the quality of word representations.
论文关键词：Multi-sense embeddings,Natural language processing,Word similarity,Synset
论文评审过程：Received 13 November 2018, Revised 29 March 2019, Accepted 13 June 2019, Available online 14 June 2019, Version of Record 28 June 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.026
