GPLSI: Word Coarse-grained Disambiguation aided by Basic Level Concepts

Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 157–160, Prague, June 2007. c⃝2007 Association for Computational Linguistics GPLSI: Word Coarse-grained Disambiguation aided by Basic Level Concepts∗ Rub´en Izquierdo Armando Su´arez GPLSI Group, DLSI University of Alicante Spain {ruben, armando}@dlsi.ua.es German Rigau IXA NLP Group EHU/UPV Donostia, Basque Country german.rigau@ehu.es Abstract We present a corpus-based supervised lear- ning system for coarse-grained sense disam- biguation. In addition to usual features for training in word sense disambiguation, our system also uses Base Level Concepts au- tomatically obtained from WordNet. Base Level Concepts are some synsets that gene- ralize a hyponymy sub–hierarchy, and pro- vides an extra level of abstraction as well as relevant information about the context of a word to be disambiguated. Our experiments proved that using this type of features re- sults on a significant improvement of preci- sion. Our system has achieved almost 0.8 F1 (fifth place) in the coarse–grained English all-words task using a very simple set of fea- tures plus Base Level Concepts annotation. 1 Introduction The GPLSI system in SemEval’s task 7, coarse– grained English all-words, consists of a corpus- based supervised-learning method which uses lo- cal context information. The system uses Base Le- vel Concepts (BLC) (Rosch, 1977) as features. In short, BLC are synsets of WordNet (WN) (Fell- baum, 1998) that are representative of a certain hy- ponymy sub–hierarchy. The synsets that are se- lected to be BLC must accomplish certain condi- tions that will be explained in next section. BLC ∗This paper has been supported by the European Union un- der the project QALL-ME (FP6 IST-033860) and the Spanish Government under the project Text-Mess (TIN2006-15265- C06-01) and KNOW (TIN2006-15049-C03-01) are slightly different from Base Concepts of Eu- roWordNet1 (EWN) (Vossen et al., 1998), Balkanet2 or Meaning Project3 because of the selection crite- ria but also because our method is capable to define them automatically. This type of features helps our system to achieve 0.79550 F1 (over the First–Sense baseline, 0.78889) while only four systems outper- formed ours being the F1 of the best one 0.83208. WordNet has been widely criticised for being a sense repository that often offers too fine–grained sense distinctions for higher level applications like Machine Translation or Question & Answering. In fact, WSD at this level of granularity, has resisted all attempts of inferring robust broad-coverage mo- dels. It seems that many word–sense distinctions are too subtle to be captured by automatic systems with the current small volumes of word–sense annotated examples. Possibly, building class-based classifiers would allow to avoid the data sparseness problem of the word-based approach. Thus, some research has been focused on deri- ving different sense groupings to overcome the fine– grained distinctions of WN (Hearst and Sch¨utze, 1993) (Peters et al., 1998) (Mihalcea and Moldo- van, 2001) (Agirre et al., 2003) and on using predefi- ned sets of sense-groupings for learning class-based classifiers for WSD (Segond et al., 1997) (Ciaramita and Johnson, 2003) (Villarejo et al., 2005) (Curran, 2005) (Ciaramita and Altun, 2006). However, …

Content truncated to 500 words