Semi-compositional Method for Synonym Extraction of Multi-Word Terms

作者: B'eatrice Daille , Amir Hazem

DOI:

关键词: Question answeringInformation retrievalSynonymTask (project management)Principle of compositionalityDistributional semanticsWeb search queryComputer scienceWord (computer architecture)Automatic summarizationArtificial intelligenceNatural language processing

摘要: Automatic synonyms and semantically related word extraction is a challenging task, useful in many NLP applications such as question answering, search query expansion, text summarization, etc. While different studies addressed the task of synonym extraction, only few investigations tackled problem acquiring multi-word terms (MWT) from specialized corpora. To extract pairs terms, we propose this paper an unsupervised semi-compositional method that makes use distributional semantics exploit compositional property shared by most MWT. We show our outperforms significantly state-of-the-art.

参考文章(24)
Philip Stuart Resnik, Selection and information: a class-based approach to lexical relationships University of Pennsylvania. ,(1993)
Hinrich Schütze, Christopher D. Manning, Prabhakar Raghavan, Introduction to Information Retrieval ,(2005)
Dekang Lin, Ming Zhou, Lijuan Qin, Shaojun Zhao, Identifying synonyms among distributionally similar words international joint conference on artificial intelligence. pp. 1492- 1493 ,(2003)
Vincent D. Blondel, Pierre P. Senellart, Automatic extraction of synonyms in a dictionary ,(2002)
Olivier Ferret, Testing Semantic Similarity Measures for Extracting Synonyms from a Corpus language resources and evaluation. ,(2010)
Jane Morris, Graeme Hirst, Non-classical lexical semantic relations north american chapter of the association for computational linguistics. pp. 46- 51 ,(2004) , 10.3115/1596431.1596438
G. Salton, M. E. Lesk, Computer Evaluation of Indexing and Text Processing Journal of the ACM. ,vol. 15, pp. 8- 36 ,(1968) , 10.1145/321439.321441