Title: Learning to translate from graded and negative relevance information

Abstract:
In my dissertation, I am looking at ways of exploiting domain specific 
information such as document-level annotations, hashtags, and cross-document 
links, as weak supervision signals in machine translation. This talk will 
focus on an approach for learning to translate by exploiting cross-lingual 
link structure in multilingual document collections. The approach uses a 
modified learning objective based on structured ramp loss, which learns from 
graded relevance information instead of reference translations, 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.