Umelb: Cross-lingual Textual Entailment with Word Alignment and String Similarity Features

Abstract

This paper describes The University of Melbourne NLP group submission to the Cross-lingual Textual Entailment shared task, our first tentative attempt at the task. The approach involves using parallel corpora and automatic word alignment to align text fragment pairs, and statistics based on unaligned words as features to classify items as forward and backward before a compositional combination into the final four classes, as well as experiments with additional string similarity features.