A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
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: http://maxent.sourceforge.netdblp:conf/tac/ShenNGK08 fatcat:qqdqctzcgngnvc7umu2v2tg3li