tailieunhanh - Báo cáo khoa học: "Multilingual WSD with Just a Few Lines of Code: the BabelNet API"

In this paper we present an API for programmatic access to BabelNet – a wide-coverage multilingual lexical knowledge base – and multilingual knowledge-rich Word Sense Disambiguation (WSD). Our aim is to provide the research community with easy-to-use tools to perform multilingual lexical semantic analysis and foster further research in this direction. | Multilingual WSD with Just a Few Lines of Code the BabelNet API Roberto Navigli and Simone Paolo Ponzetto Dipartimento di Informatica Sapienza Universita di Roma navigli ponzetto @ Abstract In this paper we present an API for programmatic access to BabelNet - a wide-coverage multilingual lexical knowledge base - and multilingual knowledge-rich Word Sense Disambiguation WSD . Our aim is to provide the research community with easy-to-use tools to perform multilingual lexical semantic analysis and foster further research in this direction. 1 Introduction In recent years research in Natural Language Processing NLP has been steadily moving towards multilingual processing the availability of ever growing amounts of text in different languages in fact has been a major driving force behind research on multilingual approaches from morpho-syntactic Das and Petrov 2011 and syntactico-semantic Peirsman and Pado 2010 phenomena to high-end tasks like textual entailment Mehdad et al. 2011 and sentiment analysis Lu et al. 2011 . These research trends would seem to indicate the time is ripe for developing methods capable of performing semantic analysis of texts written in any language however this objective is still far from being attained as is demonstrated by research in a core language understanding task such as Word Sense Disambiguation Navigli 2009 WSD continuing to be focused primarily on English. While the lack of resources has hampered the development of effective multilingual approaches to WSD recently this idea has been revamped with the organization of SemEval tasks on cross-lingual WSD Lefever and Hoste 2010 and cross-lingual lexical substitution Mihalcea et al. 2010 . In addition new research on the topic has explored the translation of sentences into many languages Navigli and Ponzetto 2010 Lefever et al. 2011 Banea and Mihalcea 2011 as well as the projection of monolingual knowledge onto another language Khapra et al. 2011 . In our research we focus on