Textual entailment recognition and its applicability in NLP tasks

Abstract

This thesis exposes the major topics in textual entailment by means of examples together with thorough discussions. As a result, an end-to-end textual entailment system was developed following the idea that textual entailment relations can be recognised from different linguistic levels. Specifically, we present three perspectives: Lexical, Syntactic and Semantic, each performing a set of useful inferences to determine entailment relations. The final entailment decision is taken by a machine learning classifier which uses as features the set of inferences from our perspectives. Extensive evaluations over the PASCAL Recognising Textual Entailment datasets have been carried out in order to estimate the contribution of different combinations of the proposed perspectives as well as demonstrate that our perspectives are complementary to each other. Furthermore, another motivation as well as a contribution of this thesis consisted of applying our system to other Natural Language Processing tasks such as Question Answering, Automatic Text Summarization and the particular semantic task of linking Wikipedia categories to WordNet glosses.