Title | ||
---|---|---|
Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation. |
Abstract | ||
---|---|---|
We present an approach to structured prediction from bandit feedback, called Bandit Structured Prediction, where only the value of a task loss function at a single predicted point, instead of a correct structure, is observed in learning. We present an application to discriminative reranking in Statistical Machine Translation (SMT) where the learning algorithm only has access to a 1-BLEU loss evaluation of a predicted translation instead of obtaining a gold standard reference translation. In our experiment bandit feedback is obtained by evaluating BLEU on reference translations without revealing them to the algorithm. This can be thought of as a simulation of interactive machine translation where an SMT system is personalized by a user who provides single point feedback to predicted translations. Our experiments show that our approach improves translation quality and is comparable to approaches that employ more informative feedback in learning. |
Year | Venue | Field |
---|---|---|
2016 | arXiv: Computation and Language | BLEU,Computer science,Machine translation,Structured prediction,Interactive machine translation,Natural language processing,Artificial intelligence,Discriminative model,Machine learning |
DocType | Volume | Citations |
Journal | abs/1601.04468 | 4 |
PageRank | References | Authors |
0.40 | 26 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Artem Sokolov | 1 | 153 | 16.08 |
Stefan Riezler | 2 | 1066 | 138.72 |
Tanguy Urvoy | 3 | 125 | 10.78 |