Characterizing pure high-order entanglements in lexical semantic spaces via information geometry.

Hou, Yuexian; Song, Dawei

Abstract

An emerging topic in Quantuam Interaction is the use of lexical semantic spaces, as Hilbert spaces, to capture the meaning of words. There has been some initial evidence that the phenomenon of quantum entanglement exists in a semantic space and can potentially play a crucial role in determining the embeded semantics. In this paper, we propose to consider pure high-order entanglements that cannot be reduced to the compositional effect of lower-order ones, as an indicator of high-level semantic entities. To characterize the intrinsic order of entanglements and distinguish pure high-order entanglements from lower-order ones, we develop a set of methods in the framework of Information Geometry. Based on the developed methods, we propose an expanded vector space model that involves context-sensitive high-order information and aims at characterizing high-level retrieval contexts. Some initial ideas on applying the proposed methods in query expansion and text classification are also presented.

Citation

HOU, Y. and SONG, D. 2009. Characterizing pure high-order entanglements in lexical semantic spaces via information geometry. In Bruza, P., Sofge, D., Lawless, W., Van Rijsbergen, K. and Klusch, M. (eds.) Proceedings of the 3rd International symposium on quantum interaction (QI 2009), 25-27 March 2009, Saarbrücken, Germany. Lecture notes in computer science, 5494. Berlin: Springer [online], pages 237-250. Available from: https://doi.org/10.1007/978-3-642-00834-4_20

• Conference Name: 3rd International symposium on quantum interaction (QI 2009)
• Conference Location: Saarbrücken, Germany
• Start Date: Mar 25, 2009
• End Date: Mar 27, 2009
• Acceptance Date: Apr 30, 2009
• Online Publication Date: Apr 30, 2009
• Publication Date: Dec 31, 2009
• Deposit Date: Aug 14, 2009
• Publicly Available Date: Aug 14, 2009
• Publisher: Springer
• Pages: 237-250
• Series Title: Lecture notes in computer science
• Series Number: 5494
• ISBN: 9783642008337
• DOI: https://doi.org/10.1007/978-3-642-00834-4_20
• Keywords: Information geometry; Pure high order entanglement; Semantic emergence; Extended vector model
• Public URL: http://hdl.handle.net/10059/396