Word Sense Disambiguation via PropStore and OntoNotes for Event Mention Detection

Abstract

In this paper, we propose a novel approach for Word Sense Disambiguation (WSD) of verbs that can be applied directly in the event mention detection task to classify event types. By using the PropStore, a database of relations between words, our approach disambiguates senses of verbs by utilizing the information of verbs that appear in similar syntactic contexts. Importantly, the resource our approach requires is only a word sense dictionary, without any annotated sentences or structures and relations between different senses (as in WordNet). Our approach can be extended to disambiguate senses of words for parts of speech besides verbs.

Chinese Word Sense Disambiguation Based on Beam Search

“…Johansson presents a new WSD method in which sense representations are embed into continuous vector space to represent words [10]. Fauceglia proposes a new method to determine event types, in which syntactic contexts of a verb are applied to select its correct sense [11]. Ponzetto extends WordNet with semantic relations from Wikipedia.…”

Automatic Approach for Word Sense Disambiguation Using Genetic Algorithms

“…Word Sense Disambiguation (WSD) is the procedure of finding the senses of the words in textual context, when word has several meanings [5].WSD is a long-standing issue in Computational Linguistics, and has main effect in many realworld applications involve machine translation, information extraction, and information retrieval [6].Word Sense Disambiguation (WSD) systems try to solve these ambiguities and finding the accurate meaning.…”