EBL-Hope: Multilingual Word Sense Disambiguation Using a Hybrid Knowledge-Based Technique

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 340–344, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics EBL-Hope: Multilingual Word Sense Disambiguation Using A Hybrid Knowledge-Based Technique Eniafe Festus Ayetiran CIRSFID, University of Bologna Via Galliera, 3 - 40121 Bologna, Italy eniafe.ayetiran2@unibo.it Guido Boella Department of Computer Science University of Turin Turin, Italy boella@di.unito.it Abstract We present a hybrid knowledge-based ap- proach to multilingual word sense disam- biguation using BabelNet. Our approach is based on a hybrid technique derived from the modified version of the Lesk algorithm and the Jiang & Conrath similarity measure. We present our system's runs for the word sense disambiguation subtask of the Multilingual Word Sense Disambiguation and Entity Link- ing task of SemEval 2015. Our system ranked 9th among the participating systems for En- glish. 1 Introduction The computational identification of the meaning of words in context is called Word Sense Disambigua- tion (WSD), also known as Lexical Disambigua- tion. There have been a significant amount of re- search on WSD over the years with numerous differ- ent approaches being explored. Multilingual word sense disambiguation aims to disambiguate the tar- get word in different languages. This, however, in- volves a different scenario compared to monolingual WSD in the sense that a single word in a language might have varying number of senses in other lan- guages with significant differences in the semantics of some of the available senses. Approaches to word sense disambiguation may be: (1) knowledge-based which depends on some knowledge dictionary or lexicon (2) supervised ma- chine learning techniques which train systems from labelled training sets and (3) unsupervised which is based on unlabelled corpora, and do not exploit any manually sense-tagged corpus to provide a sense choice for a word in context. We present a hybrid knowledge-based approach based on the Modified Lesk algorithm and the Jiang & Conrath similarity measure using BabelNet (Nav- igli and Ponzetto, 2012). The system presented here is an adaptation of our earlier work on monolingual word sense disambiguation in English (Ayetiran et al., 2014). 2 Methodology Figure 1 illustrates the general architecture of our hybrid disambiguation system. Figure 1: The Hybrid Word Sense Disambiguation Sys- tem - A system that combines two distinct disambigua- tion submodules. 340 2.1 The Lesk Algorithm Micheal Lesk (1986) invented this approach named gloss overlap or the Lesk algorithm. It is one of the first algorithms developed for the semantic disam- biguation of all words in unrestricted texts. The only resource required by the algorithm is a set of dictio- nary entries, one for each possible word sense, and knowledge about the immediate context where the sense disambiguation is performed. The idea behind the Lesk algorithm represents the seed for today's corpus-based algorithms. Almost every supervised WSD system relies one way or the other on some form of contextual overlap, with the overlap being typically measured between the context of an am- biguous word and contexts specific to various mean- ings of that word, as …

Content truncated to 500 words