A method for measuring sentence similarity and its application to conversational agents

Li, Y; Bandar, Z; McLean, D; O'Shea, J

Abstract

This paper presents a novel algorithm for computing similarity between very short texts of sentence length. It will introduce a method that takes account of not only semantic information but also word order information implied in the sentences. Firstly, semantic similarity between two sentences is derived from information from a structured lexical database and from corpus statistics. Secondly, word order similarity is computed from the position of word appearance in the sentence. Finally, sentence similarity is computed as a combination of semantic similarity and word order similarity. The proposed algorithm is applied to a real world domain of conversational agents. Experimental results demonstrated that the proposed algorithm reduces the scripter's effort to devise rule base for conversational agent.

Citation

Li, Y., Bandar, Z., McLean, D., & O'Shea, J. (2004, May). A method for measuring sentence similarity and its application to conversational agents. Presented at The 17th International Florida Artificial Intelligence Research Society (FLAIRS) Conference, Florida, USA

• Presentation Conference Type: Other
• Conference Name: The 17th International Florida Artificial Intelligence Research Society (FLAIRS) Conference
• Conference Location: Florida, USA
• Start Date: May 17, 2004
• End Date: May 19, 2004
• Publication Date: May 1, 2004
• Deposit Date: Jul 27, 2015
• Publisher URL: https://www.aaai.org/Papers/FLAIRS/2004/Flairs04-139.pdf
• Related Public URLs: http://www.flairs.com/; http://www.aaai.org/Library/FLAIRS/flairs04contents.php
• Additional Information: Event Type : Conference