Computation of Contextual Word Similarity Exploiting Syntactic and Semantic Structural Co-occurrences

• Hara Kazuo

  National Institute of Genetics

• Suzuki Ikumi

  National Institute of Genetics

• Shimbo Masashi

  Nara Institute of Science and Technology

• Matsumoto Yuji

  Nara Institute of Science and Technology

Bibliographic Information

Other Title

• 文法的・意味的共起を利用した単語類似度の計算

Abstract

We propose a new measure of semantic similarity between words in context, which exploits the syntactic/semantic structure of the context surrounding each target word. For a given pair of target words and their sentential contexts, labeled directed graphs are made from the output of a semantic parser on these sentences. Nodes in these graphs represent words in the sentences, and labeled edges represent syntactic/semantic relations between them. The similarity between the target words is then computed as the sum of the similarity of walks starting from the target words (nodes) in the two graphs. The proposed measure is tested on word sense disambiguation and paraphrase ranking tasks, and the results are promising: The proposed measure outperforms existing methods which completely ignore or do not fully exploit syntactic/semantic structural co-occurrences between a target word and its neighbors.

Journal

• Transactions of the Japanese Society for Artificial Intelligence

  Transactions of the Japanese Society for Artificial Intelligence 28 (4), 379-390, 2013

  The Japanese Society for Artificial Intelligence

Keywords

• contextual word similarity
• word sense disambiguation
• paraphrase
• kernel method

Details

• CRID: 1390001205106363264
• NII Article ID: 130003362340
• DOI: 10.1527/tjsai.28.379
• BIBCODE: 2013TJSAI..28..379H
• ISSN: 13468030
• ISSN: 13460714
• Web Site: https://www.jstage.jst.go.jp/article/tjsai/28/4/28_379/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed