Word sense disambiguation using a dictionary for sense similarity measure

Abstract

This paper presents a disambiguation method in which word senses are determined using a dictionary. We use a semantic proximity measure between words in the dictionary, taking into account the whole topology of the dictionary, seen as a graph on its entries. We have tested the method on the problem of disambiguation of the dictionary entries themselves, with promising results considering we do not use any prior annotated data.

What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language

“…Lastly, another related topic of research concerns the use of dictionaries as meaning inventories in NLP. For instance, Chodorow et al (1985), Gaume et al (2004), Tissier et al (2017) and Bosc and Vincent (2018), all employ dictionary entries for purposes ranging from word-sense disambiguation to ontology population and to embedding computation. Directly relevant here is the work of Hill et al (2016), who leverage the compositional aspect of definitions to compute sentence meaning representations.…”

Similarity estimation module for OWSCIS

“…These methods rely on an outer taxonomy to compute their distance. Other methods can use other kind of resources, such as a dictionary to compare words using the similarity between their definitions [6]. Structural similarity relies on the existing matching of the neighborhood of the concepts.…”

Towards an intelligent possibilistic web information retrieval using multiagent system

“…, n). In a HSW network, this distribution follows a power law (Douglas and Houseman, 2002) (Gaume et al, 2004) (Sergi and Ricard, 2004).…”

“…However, to be able to have this flexibility we need obviously a dictionary and especially to have structured this dictionary (all its entries) in HSW to precisely know which word is near to which other. However, there are many ways of emerging a structure of HSW starting from a dictionary (that of Gaume et al, 2004) for example consists in using words' definitions: the word w 1 is connected to the word w 2 if and only if w 2 belongs to the definition of w 1 , using this relation he deduces a ''semantic proximity'' from any word to any other). Our system SARIPOD takes again this definition and calculates the proximity between the words in order to make the query more flexible.…”