SemEval-2015 Task 13: Multilingual All-Words Sense Disambiguation and Entity Linking

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 288–297, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics SemEval-2015 Task 13: Multilingual All-Words Sense Disambiguation and Entity Linking Andrea Moro and Roberto Navigli Dipartimento di Informatica, Sapienza Universit`a di Roma, Viale Regina Elena 295, 00161 Roma, Italy {moro,navigli}@di.uniroma1.it Abstract In this paper we present the Multilingual All- Words Sense Disambiguation and Entity Link- ing task. Word Sense Disambiguation (WSD) and Entity Linking (EL) are well-known prob- lems in the Natural Language Processing field and both address the lexical ambiguity of lan- guage. Their main difference lies in the kind of meaning inventories that are used: EL uses encyclopedic knowledge, while WSD uses lexicographic information. Our aim with this task is to analyze whether, and if so, how, us- ing a resource that integrates both kinds of in- ventories (i.e., BabelNet 2.5.1) might enable WSD and EL to be solved by means of similar (even, the same) methods. Moreover, we in- vestigate this task in a multilingual setting and for some specific domains. 1 Introduction The Senseval and SemEval evaluation series rep- resent key moments in the community of compu- tational linguistics and related areas. Their focus has been to provide objective evaluations of methods within the wide spectrum of semantic techniques for tasks mainly related to automatic text understanding. Through SemEval-2015 task 13 we both continue and renew the longstanding tradition of disambigua- tion tasks, by addressing multilingual WSD and EL in a joint manner. WSD (Navigli, 2009; Navigli, 2012) is a historical task aimed at explicitly assign- ing meanings to single-word and multi-word occur- rences within text, a task which today is more alive than ever in the research community. EL (Erbs et al., 2011; Cornolti et al., 2013; Rao et al., 2013) is a more recent task which aims at discovering men- tions of entities within a text and linking them to the most suitable entry in a knowledge base. Both these tasks aim at handling the inherent ambiguity of natural language, however WSD tackles it from a lexicographic perspective, while EL tackles it from an encyclopedic one. Specifically, the main differ- ence between the two tasks lies in the kind of inven- tory they use. For instance, WordNet (Miller et al., 1990), a manually curated semantic network for the English language, has become the main reference in- ventory for English WSD systems thanks to its wide coverage of verbs, adverbs, adjectives and common nouns. More recently, Wikipedia has been shown to be an optimal resource for recovering named enti- ties, and has consequently become - together with all its semi-automatic derivations such as DBpedia (Auer et al., 2007) and Freebase (Bollacker et al., 2008) - the main reference inventory for EL systems. Over the years, the research community has typi- cally focused on each of these tasks separately. Re- cently, however, joint approaches have been pro- posed (Moro et al., 2014b). One of the reasons for pursuing the unification of these tasks …

Content truncated to 500 words