Combining Knowledge- and Corpus-based Word-Sense-Disambiguation Methods

Abstract

In this paper we concentrate on the resolution of the lexical ambiguity that arises when a given word has several different meanings. This specific task is commonly referred to as word sense disambiguation (WSD). The task of WSD consists of assigning the correct sense to words using an electronic dictionary as the source of word definitions. We present two WSD methods based on two main methodological approaches in this research area: a knowledge-based method and a corpus-based method. Our hypothesis is that word-sense disambiguation requires several knowledge sources in order to solve the semantic ambiguity of the words. These sources can be of different kinds--- for example, syntagmatic, paradigmatic or statistical information. Our approach combines various sources of knowledge, through combinations of the two WSD methods mentioned above. Mainly, the paper concentrates on how to combine these methods and sources of information in order to achieve good results in the disambiguation. Finally, this paper presents a comprehensive study and experimental work on evaluation of the methods and their combinations

Sense-Based Information Retrieval Using Fuzzy Logic and Swarm Intelligence

“…The ambiguity in the words is one of the most important open problems in natural language processing (NLP) applications that urged many researchers to innovate various approaches In order to achieve the WSD process. However, there is no WSD approach can guarantee the accuracy, large-scale, and broad-coverage [8].…”

Word Sense Disambiguation as an Integer Linear Programming Problem

“…Lexical relatedness measures can be classified in three categories: (i) measures based on dictionaries, thesauri, ontologies, or Wikipedia hyperlinks, collectively called knowledge-based measures [4,14]; (ii) corpus-based measures, which use word or sense co-occurrence statistics, like pmi and χ 2 [6,22]; and (iii) hybrid measures [16,9]. Some measures are actually intended to assess the relatedness between words (or phrases), not word senses, but they can often be modified to work with senses.…”

Detecting speculations and their scopes in scientific text

“…While designing the features, we were inspired by studies on other natural language processing problems such as Word Sense Disambiguation (WSD) and summarization. For example, machine learning methods with features based on part-of-speech tags, word stems, surrounding and co-occurring words, and dependency relationships have been successfully used in WSD (Montoyo et al, 2005;Ng and Lee, 1996;Dligach and Palmer, 2008) and positional features such as the position of a sentence in the document have been used in text summarization (e.g. (Radev et al, 2004)).…”