Contextual Encoding for Translation Quality Estimation

TL;DR

This paper introduces a neural network-based method that encodes local and global context for word-level quality estimation in machine translation, achieving top results in shared task evaluations.

Contribution

It presents a novel three-part neural network architecture that effectively captures contextual information for translation quality estimation.

Findings

Achieved first place in three of six WMT2018 QE tracks.

Effectively encodes local and global context for better predictions.

Outperforms previous approaches in translation quality estimation.

Abstract

The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and which are wrong. In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach. The first part uses an embedding layer to represent words and their part-of-speech tags in both languages. The second part leverages a one-dimensional convolution layer to integrate local context information for each target word. The third part applies a stack of feed-forward and recurrent neural networks to further encode the global context in the sentence before making the predictions. This model was submitted as the CMU entry to the WMT2018 shared task on QE, and achieves strong results, ranking first in three of the six tracks.