UMCC-DLSI: Integrative Resource for Disambiguation Task

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 427–432, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics UMCC-DLSI: Integrative resource for disambiguation task Yoan Guti´errez and Antonio Fern´andez DI, University of Matanzas Autopista a Varadero km 31/2 Matanzas, Cuba yoan.gutierrez,antonio.fernandez@umcc.cu Andr´es Montoyo and Sonia V´azquez DLSI, University of Alicante Carretera de San Vicente S/N Alicante, Spain montoyo,svazquez@dlsi.ua.es Abstract This paper describes the UMCC-DLSI system in SemEval-2010 task number 17 (All-words Word Sense Disambiguation on Specific Domain). The main purpose of this work is to evaluate and compare our computational resource of WordNet’s mappings using 3 different methods: Relevant Semantic Tree, Relevant Semantic Tree 2 and an Adaptation of k-clique’s Technique. Our proposal is a non-supervised and knowledge-based system that uses Domains Ontology and SUMO. 1 Introduction Ambiguity is the task of building up multiple alternative linguistic structures for a single input (Kozareva et al., 2007). Word Sense Disambiguation (WSD) is a key enabling- technology that automatically chooses the intended sense of a word in context. In this task, one of the most used lexical data base is WordNet (WN) (Fellbaum, 1998). WN is an online lexical reference system whose design is inspired by current psycholinguistic theories of human lexical memory. Due to the great popularity of WN in Natural Language Processing (NLP), several authors (Magnini and Cavaglia, 2000), (Niles and Pease, 2001), (Niles and Pease, 2003), (Valitutti, 2004) have proposed to incorporate to the semantic net of WN, some taxonomies that characterize, in one or several concepts, the senses of each word. In spite of the fact that there have been developed a lot of WordNet’s mappings, there isn’t one unique resource to integrate all of them in a single system approach. To solve this need we have developed a resource that joins WN1, the SUMO Ontology2, WordNet Domains3 and WordNet Affect4. Our purpose is to test the advantages of having all the resources together for the resolution of the WSD task. The rest of the paper is organized as follows. In Section 2 we describe the architecture of the integrative resource. Our approach is shown in Section 3. Next section presents the obtained results and a discussion. And finally the conclusions in Section 5. 2 Background and techniques 2.1 Architecture of the integrative resource Our integrative model takes WN 1.6 as nucleus and links to it the SUMO resource. Moreover, WordNet Domains 2.0 (WND) and WordNet Affect 1.1 (WNAffects) are also integrated but mapped instead to WN 2.0. From the model showed in Figure 1, a computational resource has been built in order to integrate the mappings above mentioned. The model integrator’s proposal provides a software that incorporates bookstores of programming classes, capable to navigate inside the semantic graph and to apply any type of possible algorithm to a net. The software architecture allows to update WN’s version. In order to maintain the compatibility with other resources mapped to WN, we have decided to use WN 1.6 version. However, the results can be …

Content truncated to 500 words