Julia Kreutzer

QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality Estimation

This paper describes the system submitted by the University of Heidelberg to the Shared Task on Word-level Quality Estimation at the 2015 Workshop on Statistical Machine Translation. The submitted system combines a continuous space deep neural network, that learns a bilingual feature representation from scratch, with a linear combination of the manually defined baseline features provided by the task organizers. A combination of these orthogonal information sources shows significant improvements over the combined systems, and produces very competitive F1-scores for predicting word-level translation quality.

Learning Structured Predictors from Bandit Feedback for Interactive NLP

Structured prediction from bandit feedback describes a learning scenario where instead of having access to a gold standard structure, a learner only receives partial feedback in form of the loss value of a predicted structure. We present new learning objectives and algorithms for this interactive scenario, focusing on convergence speed and ease of elicitability of feedback. We present supervised-to-bandit simulation experiments for several NLP tasks (machine translation, sequence labeling, text classification), showing that bandit learning from relative preferences eases feedback strength and yields improved empirical convergence.

Bandit Structured Prediction for Neural Sequence-to-Sequence Learning

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks. Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization. We present an evaluation on a neural machine translation task that shows improvements of up to 5.89 BLEU points for domain adaptation from simulated bandit feedback.