Predictor-estimator: Neuralquality estimation based on targetword prediction for machine translation

Abstract

Recently, quality estimation has been attracting increasing interest from machine translation researchers, aiming at finding a good estimator for the quality of machine translation output. The common approach for quality estimation is to treat the problem as a supervised regression/classification task using a qualityannotated noisy parallel corpus, called quality estimation data, as training data. However, the available size of quality estimation data remains small, due to the too-expensive cost of creating such data. In addition, most conventional quality estimation approaches rely on manually designed features to model nonlinear relationships between feature vectors and corresponding quality labels. To overcome these problems, this article proposes a novel neural network architecture for quality estimation task-called the predictor-estimator-that considersword prediction as an additional pre-task. The major component of the proposed neural architecture is a word prediction model based on a modified neural machine translation model-a probabilistic model for predicting a targetword conditioned on all the other source and target contexts. The underlying assumption is that the word prediction model is highly related to quality estimation models and is therefore able to transfer useful knowledge to quality estimation tasks. Our proposed quality estimation method sequentially trains the following two types of neural models: (1) Predictor: a neural word prediction model trained from parallel corpora and (2) Estimator: a neural quality estimation model trained fromquality estimation data. To transferword a prediction task to a quality estimation task, we generate quality estimation feature vectors from theword prediction model and feed them into the quality estimation model. The experimental results on WMT15 and 16 quality estimation datasets show that our proposed method has great potential in the various sub-challenges. ? 2017 ACM.