Paper: Robust Textual Inference Via Graph Matching

ACL ID H05-1049
Title Robust Textual Inference Via Graph Matching
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005

We present a system for deciding whether a given sentence can be inferred from text. Each sentence is represented as a directed graph (extracted from a depen- dency parser) in which the nodes repre- sent words or phrases, and the links repre- sent syntactic and semantic relationships. We develop a learned graph matching ap- proach to approximate entailment using the amount of the sentence’s semantic content which is contained in the text. We present results on the Recognizing Textual Entailment dataset (Dagan et al. , 2005), and show that our approach outperforms Bag-Of-Words and TF-IDF models. In ad- dition, we explore common sources of er- rors in our approach and how to remedy them.