Learning multi-prototype word embedding from single-prototype word embedding with integrated knowledge

作者：

Highlights：

• A mini context word sense disambiguation with adapted Lesk algorithm is proposed

• New initialization approach is proposed to balance speed and performance.

• Improved approximation algorithm is proposed to help supervised learning

• The framework may utilize any sense inventory with word-sense definition.

摘要

•A mini context word sense disambiguation with adapted Lesk algorithm is proposed•New initialization approach is proposed to balance speed and performance.•Improved approximation algorithm is proposed to help supervised learning•The framework may utilize any sense inventory with word-sense definition.

论文关键词：Multi-prototype word embedding,Distributional semantic model,Fine tuning,Semantic similarity

论文评审过程：Received 15 September 2015, Revised 8 March 2016, Accepted 8 March 2016, Available online 16 March 2016, Version of Record 30 March 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.03.013