On modeling sense relatedness in multi-prototype word embedding

• Main Authors: CAO, Yixin, LI, Juanzi, SHI, Jiaxin, LIU, Zhiyuan, LI, Chengjiang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7469; https://ink.library.smu.edu.sg/context/sis_research/article/8472/viewcontent/I17_1024.pdf
• Institution: Singapore Management University

To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model. However, most related work ignores the relatedness...