Alleviating Poor Context with Background Knowledge for Named Entity Disambiguation

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1903–1912, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Alleviating Poor Context with Background Knowledge for Named Entity Disambiguation Ander Barrena and Aitor Soroa and Eneko Agirre IXA NLP Group UPV/EHU University of the Basque Country Donostia, Basque Country ander.barrena,a.soroa,e.agirre@ehu.eus Abstract Named Entity Disambiguation (NED) al- gorithms disambiguate mentions of named entities with respect to a knowledge-base, but sometimes the context might be poor or misleading. In this paper we introduce the acquisition of two kinds of background information to alleviate that problem: en- tity similarity and selectional preferences for syntactic positions. We show, using a generative N¨aive Bayes model for NED, that the additional sources of context are complementary, and improve results in the CoNLL 2003 and TAC KBP DEL 2014 datasets, yielding the third best and the best results, respectively. We provide ex- amples and analysis which show the value of the acquired background information. 1 Introduction The goal of Named Entity Disambiguation (NED) is to link each mention of named entities in a docu- ment to a knowledge-base of instances. The task is also known as Entity Linking or Entity Resolution (Bunescu and Pasca, 2006; McNamee and Dang, 2009; Hachey et al., 2012). NED is confounded by the ambiguity of named entity mentions. For in- stance, according to Wikipedia, Liechtenstein can refer to the micro-state, several towns, two cas- tles or a national football team, among other in- stances. Another ambiguous entity is Derbyshire which can refer to a county in England or a cricket team. Most NED research use knowledge-bases derived or closely related to Wikipedia. For a given mention in context, NED systems (Hachey et al., 2012; Lazic et al., 2015) typically rely on two models: (1) a mention module returns possible entities which can be referred to by the mention, ordered by prior probabilities; (2) a con- Figure 1: Two examples where NED systems fail, motivating our two background models: similar entities (top) and selectional preferences (bottom). The logos correspond to the gold label. text model orders the entities according to the con- text of the mention, using features extracted from annotated training data. In addition, some systems check whether the entity is coherent with the rest of entities mentioned in the document, although (Lazic et al., 2015) shows that the coherence mod- ule is not required for top performance. Figure 1 shows two real examples from the de- velopment dataset which contains text from News, where the clues in the context are too weak or mis- leading. In fact, two mentions in those examples (Derbyshire in the first and Liechtenstein in the second) are wrongly disambiguated by a bag-of- 1903 words context model. In the first example, the context is very poor, and the system returns the county instead of the cricket team. In order to disambiguate it correctly one needs to be aware that Derbyshire, when oc- curring on News, is most notably associated with cricket. This …

Content truncated to 500 words