TEXTUAL ENTAILMENT USING LEXICAL AND SYNTACTIC SIMILARITY

A two-way Textual Entailment (TE) recognition system that uses lexical and syntactic features has beendescribed in this paper. The TE system is rule based that uses lexical and syntactic similarities. Theimportant lexical similarity features that are used in the present system are: WordNet based uni-grammatch, bi-gram match, longest common sub-sequence, skip-gram, stemming. In the syntactic TE system, the important features used are: subject-subject comparison, subject-verb comparison, object-verbcomparison and cross subject-verb comparison. The system has been separately trained on eachdevelopment corpus released as part of the Recognising Textual Entailment (RTE) competitions RTE-1, RTE-2, RTE-3 and RTE-5 and tested on the respective RTE test sets. No separate development data wasreleased in RTE-4. The evaluation results on each test set are compared with the RTE systems thatparticipated in the respective RTE competitions with lexical and syntactic approaches