UNIBA: Combining Distributional Semantic Models and Sense Distribution for Multilingual All-Words Sense Disambiguation and Entity Linking

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 360–364, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics UNIBA: Combining Distributional Semantic Models and Sense Distribution for Multilingual All-Words Sense Disambiguation and Entity Linking Pierpaolo Basile and Annalina Caputo and Giovanni Semeraro Department of Computer Science University of Bari Aldo Moro Via, E. Orabona, 4 - 70125 Bari (Italy) {pierpaolo.basile,annalina.caputo,giovanni.semeraro}@uniba.it Abstract This paper describes the participation of the UNIBA team in the Task 13 of SemEval-2015 about Multilingual All-Words Sense Disam- biguation and Entity Linking. We propose an algorithm able to disambiguate both word senses and named entities by combining the simple Lesk approach with information com- ing from both a distributional semantic model and usage frequency of meanings. The results for both English and Italian show satisfactory performance. 1 Introduction SemEval-2015 Task 13 (Moro and Navigli, 2015) aims to evaluate systems that provide a compre- hensive representation of text through linking of both words and entities with concepts in a knowl- edge base. Besides the traditional difficulties of word sense disambiguation, this task requires spe- cific methods able to tackle the challenges posed by the named entity recognition, disambiguation and linking steps. This paper proposes a unified strategy for word sense and named entity disambiguation which lever- ages BabelNet, a multilingual resource that encom- passes both encyclopedic and lexicographic knowl- edge (Navigli and Ponzetto, 2012). Our approach relies on the Distributional Lesk (DL-WSD) algo- rithm (Basile et al., 2014), which is able to disam- biguate a word occurrence by computing the similar- ity between word context and the glosses associated with all possible word meanings. Such a similarity is computed through a Distributional Semantic Model (DSM) (Sahlgren, 2006). In this work we describe an extension of the DL-WSD algorithm that exploits a specific module for entity discovery given a list of possible surface forms. In particular, we build an index in which each surface form (i.e. candidate entity) is paired to the list of all its possible meanings in a semantic net- work. This index of surface forms is exploited to look up all candidate entities in a text. The rest of this paper is structured as follows: Section 2 provides details about the adopted strat- egy, and describes the two main steps: 1) Entity Recognition and 2) Disambiguation. An experimen- tal evaluation, along with details about results, is presented in Section 3, while conclusions close the paper. 2 Methodology Our methodology is a two-step algorithm consist- ing in an initial identification of all possible entities mentioned in a text followed by the disambiguation of both words and named entities through the DL- WSD algorithm. The semantic network is exploited twice in order to 1) extract all the possible surface forms related to entities, and 2) retrieve glosses used in the disambiguation process. 2.1 Entity Recognition In order to speed up the entity recognition step we build an index in which for each surface form (en- tity) the set of all its possible meanings …

Content truncated to 500 words