Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/83272
Title: Sentence comparison using robust minimal recursion semantics and an ontology
Authors: Bond, Francis
Dridan, Rebecca.
Keywords: DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
Issue Date: 2006
Source: Dridan, R., & Bond, F. (2006). Sentence comparison using robust minimal recursion semantics and an ontology. Proceedings of the Workshop on Linguistic Distances, 35-42.
Abstract: We design and test a sentence comparison method using the framework of Robust Minimal Recursion Semantics which allows us to utilise the deep parse information produced by Jacy, a Japanese HPSG based parser and the lexical information available in our ontology. Our method was used for both paraphrase detection and also for answer sentence selection for question answering. In both tasks, results showed an improvement over Bag-of-Words, as well as providing extra information useful to the applications.
URI: https://hdl.handle.net/10356/83272
http://hdl.handle.net/10220/6824
Rights: © 2006 ACL. This paper was published in Proceedings of the Workshop on Linguistic Distances and is made available as an electronic reprint (preprint) with permission of Association for Computational Linguistics. The paper can be found at: [URL: http://aclweb.org/anthology/W/W06/W06-1106.pdf]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:HSS Conference Papers

Files in This Item:
File Description SizeFormat 
W06-1106.pdf
359.04 kBAdobe PDFThumbnail
View/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.