Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation
This addresses the challenge of personalizing machine translation systems with limited user feedback, though it is incremental as it builds on existing bandit and structured prediction frameworks.
The paper tackles the problem of learning from partial feedback in structured prediction, specifically for statistical machine translation, by proposing Bandit Structured Prediction, which uses only a single-point loss evaluation (e.g., 1-BLEU) instead of full reference translations. The result shows improved translation quality, with performance comparable to methods using more informative feedback.
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.