Paper: Addressing Ambiguity in Unsupervised Part-of-Speech Induction with Substitute Vectors

ACL ID P13-3017
Title Addressing Ambiguity in Unsupervised Part-of-Speech Induction with Substitute Vectors
Venue Annual Meeting of the Association of Computational Linguistics
Session Student Session
Year 2013
Authors

We study substitute vectors to solve the part-of-speech ambiguity problem in an unsupervised setting. Part-of-speech tag- ging is a crucial preliminary process in many natural language processing applica- tions. Because many words in natural lan- guages have more than one part-of-speech tag, resolving part-of-speech ambiguity is an important task. We claim that part- of-speech ambiguity can be solved using substitute vectors. A substitute vector is constructed with possible substitutes of a target word. This study is built on pre- vious work which has proven that word substitutes are very fruitful for part-of- speech induction. Experiments show that our methodology works for words with high ambiguity.