Cross-language learning with adversarial neural networks: Application to community question answering

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

6 Citations (Scopus)

Abstract

We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system.

Original languageEnglish
Title of host publicationCoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages226-237
Number of pages12
ISBN (Electronic)9781945626548
Publication statusPublished - 1 Jan 2017
Event21st Conference on Computational Natural Language Learning, CoNLL 2017 - Vancouver, Canada
Duration: 3 Aug 20174 Aug 2017

Publication series

NameCoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

Conference

Conference21st Conference on Computational Natural Language Learning, CoNLL 2017
CountryCanada
CityVancouver
Period3/8/174/8/17

Fingerprint

neural network
Neural networks
language
learning
community
evaluation

ASJC Scopus subject areas

  • Linguistics and Language
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Rayhan Joty, S., Nakov, P., Marques, L., & Jaradat, I. (2017). Cross-language learning with adversarial neural networks: Application to community question answering. In CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings (pp. 226-237). (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings). Association for Computational Linguistics (ACL).

Cross-language learning with adversarial neural networks : Application to community question answering. / Rayhan Joty, Shafiq; Nakov, Preslav; Marques, Lluis; Jaradat, Israa.

CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2017. p. 226-237 (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings).

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

Rayhan Joty, S, Nakov, P, Marques, L & Jaradat, I 2017, Cross-language learning with adversarial neural networks: Application to community question answering. in CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings, Association for Computational Linguistics (ACL), pp. 226-237, 21st Conference on Computational Natural Language Learning, CoNLL 2017, Vancouver, Canada, 3/8/17.
Rayhan Joty S, Nakov P, Marques L, Jaradat I. Cross-language learning with adversarial neural networks: Application to community question answering. In CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL). 2017. p. 226-237. (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings).
Rayhan Joty, Shafiq ; Nakov, Preslav ; Marques, Lluis ; Jaradat, Israa. / Cross-language learning with adversarial neural networks : Application to community question answering. CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2017. pp. 226-237 (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings).
@inproceedings{2603cd6d502f4898926309b294479e86,
title = "Cross-language learning with adversarial neural networks: Application to community question answering",
abstract = "We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system.",
author = "{Rayhan Joty}, Shafiq and Preslav Nakov and Lluis Marques and Israa Jaradat",
year = "2017",
month = "1",
day = "1",
language = "English",
series = "CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "226--237",
booktitle = "CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings",

}

TY - GEN

T1 - Cross-language learning with adversarial neural networks

T2 - Application to community question answering

AU - Rayhan Joty, Shafiq

AU - Nakov, Preslav

AU - Marques, Lluis

AU - Jaradat, Israa

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system.

AB - We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system.

UR - http://www.scopus.com/inward/record.url?scp=85053513676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053513676&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85053513676

T3 - CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

SP - 226

EP - 237

BT - CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -