TY - GEN
T1 - A hybrid textual entailment system using lexical and syntactic features
AU - Pakray, Partha
AU - Bandyopadhyay, Sivaji
AU - Gelbukh, Alexander
PY - 2010
Y1 - 2010
N2 - A two-way textual entailment (TE) recognition system that uses lexical and syntactic features has been described in this paper. Thehybrid TEsystem is based on the Support Vector Machine that uses twenty three features for lexical similarity and the output tag from a rule based syntactic two-way TE system as another feature. The important lexical features that areused in the present system are: WordNetbased unigram match, bigram match, longest c ommon s ub-sequence, s kip-gram, s temming, named entity matching and lexical distance. In the syntactic TE system, the important features used are:subject-subject comparison, subject-verb comarison, object-verb comparison and cross subject-verb comparison. The hybrid system has been developed using the collection of RTE-2 test annotated set, RTE-3 development set and RTE-3 test gold set that includes 2400 text-hypothesis p airs. Evaluation scores obtained on the RTE-4 test set (includes 1000 te xt-hypothesis pairs) show 55.30% precision and 58.40% recall for YES decisions and 55.93% precision and 52.80% recall for NO decisions.
AB - A two-way textual entailment (TE) recognition system that uses lexical and syntactic features has been described in this paper. Thehybrid TEsystem is based on the Support Vector Machine that uses twenty three features for lexical similarity and the output tag from a rule based syntactic two-way TE system as another feature. The important lexical features that areused in the present system are: WordNetbased unigram match, bigram match, longest c ommon s ub-sequence, s kip-gram, s temming, named entity matching and lexical distance. In the syntactic TE system, the important features used are:subject-subject comparison, subject-verb comarison, object-verb comparison and cross subject-verb comparison. The hybrid system has been developed using the collection of RTE-2 test annotated set, RTE-3 development set and RTE-3 test gold set that includes 2400 text-hypothesis p airs. Evaluation scores obtained on the RTE-4 test set (includes 1000 te xt-hypothesis pairs) show 55.30% precision and 58.40% recall for YES decisions and 55.93% precision and 52.80% recall for NO decisions.
KW - Dependency parsing
KW - Dependency relations
KW - Lexical distance
KW - Textual entailment
UR - http://www.scopus.com/inward/record.url?scp=78649804571&partnerID=8YFLogxK
U2 - 10.1109/COGINF.2010.5599726
DO - 10.1109/COGINF.2010.5599726
M3 - Contribución a la conferencia
AN - SCOPUS:78649804571
SN - 9781424480401
T3 - Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010
SP - 291
EP - 296
BT - Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010
T2 - 9th IEEE International Conference on Cognitive Informatics, ICCI 2010
Y2 - 7 July 2010 through 9 July 2010
ER -