The quality of a statistical machine translation (SMT) system is heavily dependent upon the amount of parallel sentences used in training. In recent years, there have been several...
We investigate the task of unsupervised constituency parsing from bilingual parallel corpora. Our goal is to use bilingual cues to learn improved parsing models for each language ...
Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few see...
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
Aria Haghighi, John Blitzer, John DeNero, Dan Klei...
During face-to-face conversation, people naturally integrate speech, gestures and higher level language interpretations to predict the right time to start talking or to give backc...