Paper: Recognising Textual Entailment With Logical Inference

ACL ID H05-1079
Title Recognising Textual Entailment With Logical Inference
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005

We use logical inference techniques for recognising textual entailment. As the performance of theorem proving turns out to be highly dependent on not read- ily available background knowledge, we incorporate model building, a technique borrowed from automated reasoning, and show that it is a useful robust method to approximate entailment. Finally, we use machine learning to combine these deep semantic analysis techniques with simple shallow word overlap; the resulting hy- brid model achieves high accuracy on the RTE testset, given the state of the art. Our results also show that the different tech- niques that we employ perform very dif- ferently on some of the subsets of the RTE corpus and as a result, it is useful to use the nature of the dataset as a feature.