Recognising Textual Entailment Focusing on Non-Entailing Text and Hypothesis

Rongzhou Shen, Thade Nahnsen, Claire Grover, Ewan Klein

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper describes a predominantly shallow ap-proach to the rte-4 Challenge. We focus our at-tention on the non-entailing Text and Hypothesis pairs in the dataset. The system uses a Maximum Entropy framework to classify each pair of Text and Hypothesis as either yes or no, using a range of different feature sets based on an analysis of the existing non-entailing pairs in rte training data.
Original languageEnglish
Title of host publicationProceedings of the Fourth PASCAL Challenges Workshop on Recognizing Textual Entailment
Number of pages8
Publication statusPublished - 2008


Dive into the research topics of 'Recognising Textual Entailment Focusing on Non-Entailing Text and Hypothesis'. Together they form a unique fingerprint.

Cite this