SHEF-NN: Translation Quality Estimation with Neural Networks
Kashif Ur Rehman Shah, Varvara Logacheva, Gustavo Henrique Paetzold, Frédéric Blain, Daniel Beck, Fethi Bougares, Lucia Specia · 2015
We describe our systems for Tasks 1 and 2 of the WMT15 Shared Task on Quality Estimation.Our submissions use (i) a continuous space language model to extract additional features for Task 1 (SHEF-GP, SHEF-SVM), (ii) a continuous bagof-words model to produce word embeddings as features for Task 2 (SHEF-W2V) and (iii) a combination of features produced by QuEst++ and a feature produced with word embedding models (SHEF-QuEst++).Our systems outperform the baseline as well as many other submissions.The results are especially encouraging for Task 2, where our best performing system (SHEF-W2V) only uses features learned in an unsupervised fashion.