Recognizing Textual Entailment Focusing on Non-Entailing Text and Hypothesis

Rongzhou Shen, Thade Nahnsen, Claire Grover, Ewan Klein
2008 Text Analysis Conference  
This paper describes a predominantly shallow approach to the rte-4 Challenge. We focus our attention 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. 1 We used a Java based maxent package in OpenNLP:
dblp:conf/tac/ShenNGK08 fatcat:qqdqctzcgngnvc7umu2v2tg3li