Entity Linking meets Word Sense Disambiguation: a Unified Approach

Entity Linking meets Word Sense Disambiguation: a Unified Approach Andrea Moro, Alessandro Raganato, Roberto Navigli Dipartimento di Informatica, Sapienza Universit`a di Roma, Viale Regina Elena 295, 00161 Roma, Italy {moro,navigli}@di.uniroma1.it ale.raganato@gmail.com Abstract Entity Linking (EL) and Word Sense Disam- biguation (WSD) both address the lexical am- biguity of language. But while the two tasks are pretty similar, they differ in a fundamen- tal respect: in EL the textual mention can be linked to a named entity which may or may not contain the exact mention, while in WSD there is a perfect match between the word form (bet- ter, its lemma) and a suitable word sense. In this paper we present Babelfy, a unified graph-based approach to EL and WSD based on a loose identification of candidate mean- ings coupled with a densest subgraph heuris- tic which selects high-coherence semantic in- terpretations. Our experiments show state-of- the-art performances on both tasks on 6 differ- ent datasets, including a multilingual setting. Babelfy is online at http://babelfy.org 1 Introduction The automatic understanding of the meaning of text has been a major goal of research in computational linguistics and related areas for several decades, with ambitious challenges, such as Machine Read- ing (Etzioni et al., 2006) and the quest for knowl- edge (Schubert, 2006). Word Sense Disambiguation (WSD) (Navigli, 2009; Navigli, 2012) is a historical task aimed at assigning meanings to single-word and multi-word occurrences within text, a task which is more alive than ever in the research community. Recently, the collaborative creation of large semi- structured resources, such as Wikipedia, and knowl- edge resources built from them (Hovy et al., 2013), such as BabelNet (Navigli and Ponzetto, 2012a), DBpedia (Auer et al., 2007) and YAGO2 (Hoffart et al., 2013), has favoured the emergence of new tasks, such as Entity Linking (EL) (Rao et al., 2013), and opened up new possibilities for tasks such as Named Entity Disambiguation (NED) and Wikifi- cation. The aim of EL is to discover mentions of entities within a text and to link them to the most suitable entry in a reference knowledge base. How- ever, in contrast to WSD, a mention may be partial while still being unambiguous thanks to the context. For instance, consider the following sentence: (1) Thomas and Mario are strikers playing in Munich. This example makes it clear how intertwined the two tasks of WSD and EL are. In fact, on the one hand, striker and play are polysemous words which can be disambiguated by selecting the game/soccer playing senses of the two words in a dictionary; on the other hand, Thomas and Mario are partial men- tions which have to be linked to the appropriate en- tries of a knowledge base, that is, Thomas M¨uller and Mario Gomez, two well-known soccer players. The two main differences between WSD and EL lie, on the one hand, in the kind of inventory used, i.e., dictionary vs. encyclopedia, and, on the other hand, in the assumption that the mention is complete or potentially partial. Notwithstanding …

Content truncated to 500 words