This paper describes the recurrent neural network based model for translation quality estimation. Recurrent neural network based quality estimation model consists of two parts. The first part using two bidirectional recurrent neural networks generates the quality information about whether each word in translation is properly translated. The second part using another recurrent neural network pre...

We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to evaluation metrics. Experiments on Chinese-English and EnglishFrench translation show that our approach achieves significant improvements over maximum likelihood estimation on a sta...

Much of an instructor’s time is spent on the management and grading of homework. We present the Machine Translation Leaderboard, a platform for managing, displaying, and automatically grading homework assignments. It runs on Google App Engine, which provides hosting and usermanagement services. Among its many features are the ability to easily define new assignments, manage submission histories...

Activating Group 1 (Gp1) metabotropic glutamate receptors (mGluRs), including mGluR1 and mGluR5, elicits translation-dependent neural plasticity mechanisms that are crucial to animal behavior and circuit development. Dysregulated Gp1 mGluR signaling has been observed in numerous neurological and psychiatric disorders. However, the molecular pathways underlying Gp1 mGluR-dependent plasticity mec...

Neural Machine Translation (NMT) systems, introduced only in 2013, have achieved state of the art results in many MT tasks. MetaMind’s submissions to WMT ’16 seek to push the state of the art in one such task, English→German newsdomain translation. We integrate promising recent developments in NMT, including subword splitting and back-translation for monolingual data augmentation, and introduce...

Communication is the cornerstone of medicine, without which we cannot interact with our patients. The General Medical Council’s Good Medical Practice states that “Doctors must listen to patients, take account of their views, and respond honestly to their questions.” However, we still often interact with patients who do not speak the local language. In the United Kingdommost hospitals have acces...

This paper describes the Johns Hopkins University submissions to the shared translation task of EMNLP 2017 Second Conference on Machine Translation (WMT 2017). We set up phrase-based, syntax-based and/or neural machine translation systems for all 14 language pairs of this year’s evaluation campaign. We also performed neural rescoring of phrasebased systems for English-Turkish and English-Finnish.

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the sourceand target-side local context information. In practice, distinguishing good translations from bad ones does not only depend on the local features, but also rely on the global sentence-level information. In this pape...