Machine translation evaluation meets community question answering

Francisco Guzmán, Lluis Marques, Preslav Nakov

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

19 Citations (Scopus)

Abstract

We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages460-466
Number of pages7
ISBN (Electronic)9781510827592
Publication statusPublished - 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: 7 Aug 201612 Aug 2016

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period7/8/1612/8/16

Fingerprint

Network architecture
Neural networks
Syntactics
evaluation
neural network
community
Semantics
ranking
semantics
Evaluation
Question Answering
Machine Translation
interaction
performance
Neural Networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Linguistics and Language
  • Software
  • Language and Linguistics

Cite this

Guzmán, F., Marques, L., & Nakov, P. (2016). Machine translation evaluation meets community question answering. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers (pp. 460-466). Association for Computational Linguistics (ACL).

Machine translation evaluation meets community question answering. / Guzmán, Francisco; Marques, Lluis; Nakov, Preslav.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), 2016. p. 460-466.

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

Guzmán, F, Marques, L & Nakov, P 2016, Machine translation evaluation meets community question answering. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), pp. 460-466, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 7/8/16.
Guzmán F, Marques L, Nakov P. Machine translation evaluation meets community question answering. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL). 2016. p. 460-466
Guzmán, Francisco ; Marques, Lluis ; Nakov, Preslav. / Machine translation evaluation meets community question answering. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), 2016. pp. 460-466
@inproceedings{775d544fa86d4186b9a0611db54fac8e,
title = "Machine translation evaluation meets community question answering",
abstract = "We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.",
author = "Francisco Guzm{\'a}n and Lluis Marques and Preslav Nakov",
year = "2016",
language = "English",
pages = "460--466",
booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Machine translation evaluation meets community question answering

AU - Guzmán, Francisco

AU - Marques, Lluis

AU - Nakov, Preslav

PY - 2016

Y1 - 2016

N2 - We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.

AB - We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.

UR - http://www.scopus.com/inward/record.url?scp=85016648214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016648214&partnerID=8YFLogxK

M3 - Conference contribution

SP - 460

EP - 466

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers

PB - Association for Computational Linguistics (ACL)

ER -