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


This paper describes The University of Melbourne NLP group submission to the Crosslingual 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… (More)


1 Figure or Table

Slides referencing similar topics