NUIG-UNLP at SemEval-2016 Task 13: A Simple Word Embedding-based Approach for Taxonomy Extraction

Proceedings of SemEval-2016, pages 1298–1302, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics NUIG-UNLP at SemEval-2016 Task 13: A Simple Word Embedding-based Approach for Taxonomy Extraction Joel Pocostales Insight Centre for Data Analytics National University of Ireland, Galway name.surname@insight-centre.org Abstract This paper describes the NUIG-UNLP sys- tem submitted to SemEval-2016, Task 13. We implement a semi-supervised method that ex- tracts hypernym candidates for the terms pro- vided in the test list. The main assumption of our system is that hypernyms may be induced by adding a vector offset to the corresponding hyponym word embedding. The vector off- set is obtained as the average offset between 200 pairs of hyponym-hypernym in the same vector space. Our approach ranked second on connectivity (c.c.) and categorisation (i.i.) for the English taxonomy construction, and fifth on the overall ranking. Despite of these mod- est results, our system achieved comparable evaluations scores with the other participants. 1 Introduction Hyponyms and hypernyms (sometimes called sub- ordinate and superordinate terms, respectively) de- scribe a type of relation which, in general, can be defined in terms of asymmetric entailment: given the hyponym of feline, cat, and its hypernym, feline, we can state that all cats are felines, but not that all felines are cats. Likewise, the relations that hyponyms and hyper- nyms signal can also be characterized as a isa rela- tion between a hyponym X and hypernym Y : for nouns, X is a Kind of Y or X is a type of Y (Saint- Dizier and Viegas, 1995). These particular type / kind-of relations form the backbone of the construc- tion of Lexical Taxonomies and Ontologies (Buite- laar et al., 2004; Navigli et al., 2011), and those in turn plays a essential role in many Natural Lan- guage Processing applications: Question Answer- ing, Textual Entailment, Natural Language Infer- ence, or Text Summarization (Bordea et al., 2015). In this regard, despite the fact that taxonomy construction can be addressed from a diversity of approaches, the lexico-syntactic patterns-based are still the most widely used. Nevertheless, in the last years some vector space-based approaches have emerged for learning semantic hierarchies (Saxe et al., 2013; Khashabi, 2013; Fu et al., 2014; Rei and Briscoe, 2014; Tan et al., 2015; Nayak, 2015). In the next sections we will mainly turn our attention to this type of approaches. 1.1 Task Definition The five participating teams in SemEval-2016 Task 13 were provided with six datasets in four lan- guages (English, Dutch, French and Italian)1. The datasets can be divided in three domains (science, environment and food). Additionally, this year the TExEval-2 task has a focus in four subtasks related to taxonomy construction: 1. Taxonomy construction 2. Hypernym identification 3. Multilingual taxonomy construction 4. Multilingual hypernym identification However, due to lack of time, we decided to ad- dress only the English monolingual subtasks. 1The corresponding system description papers can be found in Cleuziou and Moreno (2016), Panchenko et al. (2016) and Tan (2016). 1298 The key idea behind TExEval tasks is …

Content truncated to 500 words