Contextual Encoding for Translation Quality Estimation
This work addresses the problem of predicting translation errors for machine translation users, but it is incremental as it builds on existing neural approaches for quality estimation.
The paper tackles word-level translation quality estimation by proposing a neural network method that encodes local and global context, achieving first place in three out of six tracks in the WMT2018 shared task.
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.