Pairwise neural machine translation evaluation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)

Abstract

We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic and semantic information from the reference and the two hypotheses is compacted into relatively small distributed vector representations, and fed into a multi-layer neural network that models the interaction between each of the hypotheses and the reference, as well as between the two hypotheses. These compact representations are in turn based on word and sentence embeddings, which are learned using neural networks. The framework is flexible, allows for efficient learning and classification, and yields correlation with humans that rivals the state of the art.

Original languageEnglish
Title of host publicationACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages805-814
Number of pages10
Volume1
ISBN (Print)9781941643723
Publication statusPublished - 2015
Event53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
Duration: 26 Jul 201531 Jul 2015

Other

Other53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
CountryChina
CityBeijing
Period26/7/1531/7/15

Fingerprint

Neural networks
Multilayer neural networks
Syntactics
Semantics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Guzman, F., Rayhan Joty, S., Marques, L., & Nakov, P. (2015). Pairwise neural machine translation evaluation. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 1, pp. 805-814). Association for Computational Linguistics (ACL).

Pairwise neural machine translation evaluation. / Guzman, Francisco; Rayhan Joty, Shafiq; Marques, Lluis; Nakov, Preslav.

ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2015. p. 805-814.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Guzman, F, Rayhan Joty, S, Marques, L & Nakov, P 2015, Pairwise neural machine translation evaluation. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. vol. 1, Association for Computational Linguistics (ACL), pp. 805-814, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 26/7/15.
Guzman F, Rayhan Joty S, Marques L, Nakov P. Pairwise neural machine translation evaluation. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1. Association for Computational Linguistics (ACL). 2015. p. 805-814
Guzman, Francisco ; Rayhan Joty, Shafiq ; Marques, Lluis ; Nakov, Preslav. / Pairwise neural machine translation evaluation. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2015. pp. 805-814
@inproceedings{71f596a99ef34f468d2949e2feb05967,
title = "Pairwise neural machine translation evaluation",
abstract = "We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic and semantic information from the reference and the two hypotheses is compacted into relatively small distributed vector representations, and fed into a multi-layer neural network that models the interaction between each of the hypotheses and the reference, as well as between the two hypotheses. These compact representations are in turn based on word and sentence embeddings, which are learned using neural networks. The framework is flexible, allows for efficient learning and classification, and yields correlation with humans that rivals the state of the art.",
author = "Francisco Guzman and {Rayhan Joty}, Shafiq and Lluis Marques and Preslav Nakov",
year = "2015",
language = "English",
isbn = "9781941643723",
volume = "1",
pages = "805--814",
booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Pairwise neural machine translation evaluation

AU - Guzman, Francisco

AU - Rayhan Joty, Shafiq

AU - Marques, Lluis

AU - Nakov, Preslav

PY - 2015

Y1 - 2015

N2 - We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic and semantic information from the reference and the two hypotheses is compacted into relatively small distributed vector representations, and fed into a multi-layer neural network that models the interaction between each of the hypotheses and the reference, as well as between the two hypotheses. These compact representations are in turn based on word and sentence embeddings, which are learned using neural networks. The framework is flexible, allows for efficient learning and classification, and yields correlation with humans that rivals the state of the art.

AB - We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic and semantic information from the reference and the two hypotheses is compacted into relatively small distributed vector representations, and fed into a multi-layer neural network that models the interaction between each of the hypotheses and the reference, as well as between the two hypotheses. These compact representations are in turn based on word and sentence embeddings, which are learned using neural networks. The framework is flexible, allows for efficient learning and classification, and yields correlation with humans that rivals the state of the art.

UR - http://www.scopus.com/inward/record.url?scp=84943748824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943748824&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781941643723

VL - 1

SP - 805

EP - 814

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -