SyntagNet: Challenging Supervised Word Sense Disambiguation with Lexical-Semantic Combinations

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 3534–3540, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 3534 SyntagNet: Challenging Supervised Word Sense Disambiguation with Lexical-Semantic Combinations Marco Maru1,2, Federico Scozzafava1, Federico Martelli1,3, and Roberto Navigli1 1Department of Computer Science, Sapienza University of Rome 2Department of Literature and Modern Cultures, Sapienza University of Rome 3Babelscape srl, Italy firstname.lastname@uniroma1.it, martelli@babelscape.com Abstract Current research in knowledge-based Word Sense Disambiguation (WSD) indicates that performances depend heavily on the Lexical Knowledge Base (LKB) employed. This pa- per introduces SyntagNet, a novel resource consisting of manually disambiguated lexical- semantic combinations. By capturing sense distinctions evoked by syntagmatic relations, SyntagNet enables knowledge-based WSD systems to establish a new state of the art which challenges the hitherto unrivaled perfor- mances attained by supervised approaches. To the best of our knowledge, SyntagNet is the first large-scale manually-curated resource of this kind made available to the community (at http://syntagnet.org). 1 Introduction Word Sense Disambiguation (WSD) is one of the most challenging Natural Language Processing (NLP) tasks. It deals with lexical ambiguity, and it is core to achieving the much-sought-for goal of Natural Language Understanding (Navigli, 2018). In a broad sense, two major approaches can be adopted for performing WSD: the supervised and the knowledge-based ones. Supervised methods, which learn a classifier from training data, have improved from 65% (Sny- der and Palmer, 2004) to over 71% accuracy, thus proving to perform best for WSD purposes (Yuan et al., 2016; Melacci et al., 2018; Uslu et al., 2018). However, supervision depends heavily on large quantities of reliable sense-annotated data which – especially for languages other than English – are poorly available. As a major alternative to supervised WSD, knowledge-based approaches drop the require- ment for large amounts of training data by draw- ing on rich Lexical Knowledge Bases (LKB) such as WordNet (Fellbaum, 1998), and allow scaling to multiple languages thanks to multilingual re- sources such as BabelNet (Navigli and Ponzetto, 2012). The structure of an LKB plays a key role in increasing the overall disambiguation per- formance. For the purposes of WSD, a criti- cal consideration concerns the nature of the rela- tions connecting concepts: while LKBs tend to fo- cus on the paradigmatic dimension of language, such resources fall short in respect of syntagmatic relations1, which are also crucial for sense dis- ambiguation due to interconnecting co-occurring words (Navigli and Lapata, 2010). In this paper we address this deficiency and present, for the first time, a manually- curated large-scale lexical-semantic combination2 database which associates pairs of concepts with pairs of co-occurring words. Importantly, we prove the effectiveness of our resource by achiev- ing the state of the art in multilingual knowledge- based WSD and by matching supervised WSD performances when integrated into an LKB made up of WordNet and the Princeton WordNet Gloss Corpus3. 2 Related work Several studies on knowledge-based algorithms have indicated that the LKB structure is of …

Content truncated to 500 words