TALP at TAC 2008: A Semantic Approach to Recognizing Textual Entailment
نویسندگان
چکیده
This paper describes our experiments on Textual Entailment in the context of the Fourth Recognising Textual Entailment (RTE-4) Evaluation Challenge at TAC 2008 contest. Our system uses a Machine Learning approach with AdaBoost to deal with the RTE challenge. We perform a lexical, syntactic, and semantic analysis of the entailment pairs. From this information we compute a set of semantic-based distances between sentences. We improved our baseline system for the RTE-3 challenge with more Language Processing techniques, an hypothesis classifier, and new semantic features. The results show no general improvement with respect to the baseline.
منابع مشابه
WHU at TAC 2009: A Tri-categorization Approach to Textual Entailment Recognition
This paper describes our system of recognizing textual entailment for RTE-5 challenge at TAC 2009. We propose a textual entailment recognition framework and implement a system of classification which takes lexical, syntactic and semantic features as considered. To improve the performance, some lexical-semantic resources and web knowledge bases are also incorporated in the system. Official resul...
متن کاملRecognizing Textual Entailment at RTE4 with CERES
This paper reports on the performance of a new system for recognizing textual entailment. We present a brief overview of the CERES system and summarize its semantic alignment method for determining entailment. Then, we describe the experiments that were performed, both official and subsequently, against the RTE4 test dataset. We also report on comparison runs against the previous RTE3 developme...
متن کاملCombining Lexical, Syntactic, and Semantic Evidence for Textual Entailment Classification
This paper describes the Emory system for recognizing textual entailment as used for the RTE4 track at the TAC 2008 competition. We use a supervised machine learning approach to train a classifier over a variety of lexical, syntactic, and semantic metrics. We treat the output of each metric as a feature, and train a classifier on the provided data from the previous RTE tracks. As a result, our ...
متن کاملTAC 2008 CLEAR RTE System Report: Facet-based Entailment
This paper describes the CLEAR team’s submission to the 2008 Text Analysis Conference under the Recognizing Textual Entailment track. The system breaks text fragments down into fine-grained semantic facets and performs entailment recognition on these. We show that, in the relevant subset of the data, we can achieve 90% accuracy in pinpointing the specific facet of a hypothesis that is not entai...
متن کاملSagan in TAC2009: Using Support Vector Machines in Recognizing Textual Entailment and TE Search Pilot task
This paper describes the Sagan system in the context of the Fifth Pascal Recognizing Textual Entailment (RTE-5) Evaluation Challenge and the new Textual Entailment Search Pilot Task. The system employs a Support Vector Machine classifier with a set of 32 features, which includes lexical and semantic similarity for both two-way and three-way classification tasks. Additionally, we show an approac...
متن کامل