Paper: A Tale about PRO and Monsters

ACL ID P13-2003
Title A Tale about PRO and Monsters
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

While experimenting with tuning on long sentences, we made an unexpected discov- ery: that PRO falls victim to monsters ? overly long negative examples with very low BLEU+1 scores, which are unsuitable for learning and can cause testing BLEU to drop by several points absolute. We propose several effective ways to address the problem, using length- and BLEU+1- based cut-offs, outlier filters, stochastic sampling, and random acceptance. The best of these fixes not only slay and pro- tect against monsters, but also yield higher stability for PRO as well as improved test- time BLEU scores. Thus, we recommend them to anybody using PRO, monster- believer or not. 1 Once Upon a Time... For years, the standard way to do statistical ma- chine translation parameter tuning has been to use minimum erro...