Indexed by:
Abstract:
Recognizing Textual Entailment (RTE) task is defined as recognizing, given two text fragments T(Text) and H (Hypothesis), whether the meaning of H can be inferred from T. This paper discusses multiple techniques to implement the task, including lexical matching, semantic matching and syntactic matching methods. Word overlap is the basic technology and the part-of-speech is applied for the improvement of lexical matching approach. WordNet resource is exploited for the semantic matching. Especially, the strict matching and fuzzy matching of dependency relations are used for implementing the syntactic matching method. Finally, the system has been evaluated on the data set of RTE-3, RTE-4 and RTE-5. We also explore the effect of different techniques on system performance. The best accuracy is 57.4% for 3-way task and 60.2% for 2-way task. Copyright © 2011 Binary Information Press.
Keyword:
Reprint Author's Address:
Email:
Source :
Journal of Computational Information Systems
ISSN: 1553-9105
Year: 2011
Issue: 7
Volume: 7
Page: 2403-2411
Cited Count:
WoS CC Cited Count: 0
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 10
Affiliated Colleges: