Imperial College London
Portrait Picture

Professor Lucia Specia

Faculty of Engineering, Department of Computing

Chair in Natural Language Processing
 
 
 
//

Contact

 

l.specia Website

 
 
//

Location

 

572aHuxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Fomicheva:2020:10.1162/tacl_a_00330,
author = {Fomicheva, M and Sun, S and Yankovskaya, L and Blain, F and Guzmán, F and Fishel, M and Aletras, N and Chaudhary, V and Specia, L},
doi = {10.1162/tacl_a_00330},
journal = {Transactions of the Association for Computational Linguistics},
pages = {539--555},
title = {Unsupervised quality estimation for neural machine translation},
url = {http://dx.doi.org/10.1162/tacl_a_00330},
volume = {8},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time. Existing approaches require large amounts of expert annotated data, computation and time for training. As an alternative, we devise an unsupervised approach to QE where no training or access to additional resources besides the MT system itself is required. Different from most of the current work that treats the MT system as a black box, we explore useful information that can be extracted from the MT system as a by-product of translation. By employing methods for uncertainty quantification, we achieve very good correlation with human judgments of quality, rivalling state-of-the-art supervised QE models. To evaluate our approach we collect the first dataset that enables work on both black-box and glass-box approaches to QE.
AU  - Fomicheva,M
AU  - Sun,S
AU  - Yankovskaya,L
AU  - Blain,F
AU  - Guzmán,F
AU  - Fishel,M
AU  - Aletras,N
AU  - Chaudhary,V
AU  - Specia,L
DO  - 10.1162/tacl_a_00330
EP  - 555
PY  - 2020///
SN  - 2307-387X
SP  - 539
TI  - Unsupervised quality estimation for neural machine translation
T2  - Transactions of the Association for Computational Linguistics
UR  - http://dx.doi.org/10.1162/tacl_a_00330
UR  - https://www.mitpressjournals.org/doi/full/10.1162/tacl_a_00330
UR  - http://hdl.handle.net/10044/1/84005
VL  - 8
ER  -
Download