Lexico-Syntactic subsumption for textual entailment


In this paper a graph-based approach to the task of textual entailment between a Text and Hypothesis is presented. The approach takes into account the full lexico-syntactic context of both the Text and Hypothesis and relies heavily on the concept of subsumption. It starts with mapping the Text and Hypothesis into graphstructures where nodes represent concepts and edges represent lexico-syntactic relations among concepts. Based on a subsumption score between the Text-graph and Hypothesis-graph an entailment decision is made. A novel feature of our approach is the handling of negation. The results obtained from a standard entailment test data set are better than results reported by systems that use similar knowledge resources. We also found that a tf-idf approach performs close to chance for sentence-like Texts and Hypotheses.

Publication Title

International Conference Recent Advances in Natural Language Processing, RANLP

This document is currently not available here.