Learning to translate from graded and negative relevance information

摘要

We present an approach for learning to translate by exploiting cross-lingual link structure in multilingual document collections. We propose a new learning objective based on structured ramp loss, which learns from graded relevance, explicitly including negative relevance information. Our results on English German translation of Wikipedia entries show small, but significant, improvements of our method over an unadapted baseline, even when only a weak relevance signal is used. We also compare our method to monolingual language model adaptation and automatic pseudo-parallel data extraction and find small improvements even over these strong baselines.