QuEst QuEst - an open source tool for translation quality estimation


PASCAL2, Harvest program


This project puts together many of the European leading researchers in quality estimation for machine translation to share their expertise in the field and: (i) jointly build an open source system for the problem; (ii) exploit new avenues for research in the field. Quality estimation for language output tasks such as machine translation is commonly framed as a supervised machine learning task. As such, it poses a number of challenging problems, such as the fact that it can exploit a large, diverse, but often noisy set of information sources, with a relatively small number of annotated data points, and it relies on human annotations that are often inconsistent due to the subjectivity of the task (quality judgements). Also, different applications for the quality predictions may benefit from different machine learning techniques, an aspect that has been mostly neglected so far. In addition to developing a state of the art, robust open source system to predict quality scores of machine translations aimed at different tasks, this project investigates ways of assessing the utility of the quality predictions in novel extrinsic tasks, such as self-learning of statistical machine translation systems.


October-December 2012


Coordinators Affiliation Country
Lucia Specia University of Sheffield UK
Trevor Cohn University of Sheffield UK
Jose Guilherme Camargo de Souza FBK Italy
Kashif Shah University of Sheffield UK
Christian Buck University of Edinburgh UK
Chirstian Hardmeier Uppsala University Sweden
David Langlois LORIA Institute France
Eleftherios Avramidis DFKI Germany
Erwan Moreau Trinity College Dublin Ireland
Eva Hasler University of Edinburgh UK
Isaias Sanchez-Cortina Universitat Politecnica de Valencia Spain
Luong Ngoc Quang Grenoble University France
Raphael Rubino Dublin City University and Symantec Ireland


You can download the software from here.