A Unified Multilingual Semantic Representation of Concepts

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 741–751, Beijing, China, July 26-31, 2015. c⃝2015 Association for Computational Linguistics A Unified Multilingual Semantic Representation of Concepts Jos´e Camacho-Collados, Mohammad Taher Pilehvar and Roberto Navigli Department of Computer Science Sapienza University of Rome {collados,pilehvar,navigli}@di.uniroma1.it Abstract Semantic representation lies at the core of several applications in Natural Language Processing. However, most existing se- mantic representation techniques cannot be used effectively for the representation of individual word senses. We put for- ward a novel multilingual concept repre- sentation, called MUFFIN, which not only enables accurate representation of word senses in different languages, but also pro- vides multiple advantages over existing approaches. MUFFIN represents a given concept in a unified semantic space irre- spective of the language of interest, en- abling cross-lingual comparison of differ- ent concepts. We evaluate our approach in two different evaluation benchmarks, se- mantic similarity and Word Sense Disam- biguation, reporting state-of-the-art per- formance on several standard datasets. 1 Introduction Semantic representation, i.e., the task of represent- ing a linguistic item (such as a word or a word sense) in a mathematical or machine-interpretable form, is a fundamental problem in Natural Lan- guage Processing (NLP). The Vector Space Model (VSM) is a prominent approach for semantic rep- resentation, with widespread popularity in numer- ous NLP applications. The prevailing methods for the computation of a vector space represen- tation are based on distributional semantics (Har- ris, 1954). However, these approaches, whether in their conventional co-occurrence based form (Salton et al., 1975; Turney and Pantel, 2010; Lan- dauer and Dooley, 2002), or in their newer predic- tive branch (Collobert and Weston, 2008; Mikolov et al., 2013; Baroni et al., 2014), suffer from a major drawback: they are unable to model indi- vidual word senses or concepts, as they conflate different meanings of a word into a single vecto- rial representation. This hinders the functionality of this group of vector space models in tasks such as Word Sense Disambiguation (WSD) that re- quire the representation of individual word senses. There have been several efforts to adapt and apply distributional approaches to the representation of word senses (Pantel and Lin, 2002; Brody and La- pata, 2009; Reisinger and Mooney, 2010; Huang et al., 2012). However, none of these techniques provides representations that are already linked to a standard sense inventory, and consequently such mapping has to be carried out either manually, or with the help of sense-annotated data. Chen et al. (2014) addressed this issue and obtained vectors for individual word senses by leveraging WordNet glosses. NASARI (Camacho-Collados et al., 2015) is another approach that obtains ac- curate sense-specific representations by combin- ing the complementary knowledge from Word- Net and Wikipedia. Graph-based approaches have also been successfully utilized to model individ- ual words (Hughes and Ramage, 2007; Agirre et al., 2009; Yeh et al., 2009), or concepts (Pilehvar et al., 2013; Pilehvar and Navigli, 2014), drawing on the structural …

Content truncated to 500 words