Lexical Coverage Evaluation of Large-scale Multilingual Semantic Lexicons for Twelve Languages

Lexical Coverage Evaluation of Large-scale Multilingual Semantic Lexicons for Twelve Languages Scott Piao1, Paul Rayson1, Dawn Archer2, Francesca Bianchi3, Carmen Dayrell1, Mahmoud El-Haj1, Ricardo-María Jiménez4, Dawn Knight5, Michal Křen6 , Laura Löfberg1, Rao Muhammad Adeel Nawab7, Jawad Shafi1, Phoey Lee Teh8, Olga Mudraya9 1Lancaster University, UK; 2Manchester Metropolitan University, UK; 3University of Salento, Italy, 4Universitat Internacional de Catalunya, Spain; 5Cardiff University, UK; 6Charles University in Prague, Czech Republic; 7COMSATS Institute of Information technology, Pakistan; 8Sunway University, Malaysia; 9Independent Researcher, UK E-mail: s.piao@lancaster.ac.uk, p.rayson@lancaster.ac.uk,d.archer@mmu.ac.uk, francesca.bianchi@unisalento.it, c.dayrell@lancaster.ac.uk, m.el-haj@lancaster.ac.uk, rmjimenez@uic.es, knightd5@cardiff.ac.uk, michal.kren@ff.cuni.cz, l.lofberg@lancaster.ac.uk, adeelnawab@ciitlahore.edu.pk, jawadshafi@ciitlahore.edu.pk, phoeyleet@sunway.edu.my, olga.mudraya@ntlworld.com Abstract The last two decades have seen the development of various semantic lexical resources such as WordNet (Miller, 1995) and the USAS semantic lexicon (Rayson et al., 2004), which have played an important role in the areas of natural language processing and corpus-based studies. Recently, increasing efforts have been devoted to extending the semantic frameworks of existing lexical knowledge resources to cover more languages, such as EuroWordNet and Global WordNet. In this paper, we report on the construction of large-scale multilingual semantic lexicons for twelve languages, which employ the unified Lancaster semantic taxonomy and provide a multilingual lexical knowledge base for the automatic UCREL semantic annotation system (USAS). Our work contributes towards the goal of constructing larger-scale and higher-quality multilingual semantic lexical resources and developing corpus annotation tools based on them. Lexical coverage is an important factor concerning the quality of the lexicons and the performance of the corpus annotation tools, and in this experiment we focus on evaluating the lexical coverage achieved by the multilingual lexicons and semantic annotation tools based on them. Our evaluation shows that some semantic lexicons such as those for Finnish and Italian have achieved lexical coverage of over 90% while others need further expansion. Keywords: semantic lexicon, multilingual lexicons, semantic annotation, lexical coverage, corpus annotation tool, multilingualism 1. Introduction This paper reports on the construction of large-scale multilingual semantic lexicons for twelve languages, which have been designed to employ a unified semantic classification scheme and to form the knowledge bases for an automatic multilingual semantic annotation system. Over the past two decades, we have seen the development of various semantic lexical resources such as WordNet1 and the USAS semantic lexicon (Rayson et al., 2004), which are playing an important role in the areas of natural language processing, corpus-based language studies and information system development. More recently, increasing efforts have been devoted to extending the semantic frameworks of existing lexical knowledge resources to cover more languages: see, e.g., EuroWordNet (Vossen, 1998), and the Global WordNet2 etc. Creating multilingual resources around a common unified framework is an important endeavour as it supports not only monolingual research in those languages, but also cross-lingual and multilingual research directly. Such aspects are becoming even more important in a number of application scenarios and research settings such as speech-to-speech machine translation, cross-lingual text reuse and plagiarism detection, summarisation and information retrieval. 1 https://wordnet.princeton.edu/wordnet 2For details of Global WordNet, see http://globalwordnet.org/wordnets-in-the-world Our work contributes towards the goal …

Content truncated to 500 words