Semi-supervised question retrieval with gated convolutions

Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Katerina Tymoshenko, Alessandro Moschitti, Lluis Marques

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

23 Citations (Scopus)

Abstract

Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).1

Original languageEnglish
Title of host publication2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1279-1289
Number of pages11
ISBN (Electronic)9781941643914
Publication statusPublished - 2016
Event15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - San Diego, United States
Duration: 12 Jun 201617 Jun 2016

Other

Other15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
CountryUnited States
CitySan Diego
Period12/6/1617/6/16

Fingerprint

Convolution
CNN
Network architecture
neural network
Semantics
semantics
Neural networks
methodology
ability
evaluation
Annotation

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Cite this

Lei, T., Joshi, H., Barzilay, R., Jaakkola, T., Tymoshenko, K., Moschitti, A., & Marques, L. (2016). Semi-supervised question retrieval with gated convolutions. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference (pp. 1279-1289). Association for Computational Linguistics (ACL).

Semi-supervised question retrieval with gated convolutions. / Lei, Tao; Joshi, Hrishikesh; Barzilay, Regina; Jaakkola, Tommi; Tymoshenko, Katerina; Moschitti, Alessandro; Marques, Lluis.

2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), 2016. p. 1279-1289.

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

Lei, T, Joshi, H, Barzilay, R, Jaakkola, T, Tymoshenko, K, Moschitti, A & Marques, L 2016, Semi-supervised question retrieval with gated convolutions. in 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 1279-1289, 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016, San Diego, United States, 12/6/16.
Lei T, Joshi H, Barzilay R, Jaakkola T, Tymoshenko K, Moschitti A et al. Semi-supervised question retrieval with gated convolutions. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL). 2016. p. 1279-1289
Lei, Tao ; Joshi, Hrishikesh ; Barzilay, Regina ; Jaakkola, Tommi ; Tymoshenko, Katerina ; Moschitti, Alessandro ; Marques, Lluis. / Semi-supervised question retrieval with gated convolutions. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), 2016. pp. 1279-1289
@inproceedings{648847b580ff4347872c2ee3ebb610f4,
title = "Semi-supervised question retrieval with gated convolutions",
abstract = "Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).1",
author = "Tao Lei and Hrishikesh Joshi and Regina Barzilay and Tommi Jaakkola and Katerina Tymoshenko and Alessandro Moschitti and Lluis Marques",
year = "2016",
language = "English",
pages = "1279--1289",
booktitle = "2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Semi-supervised question retrieval with gated convolutions

AU - Lei, Tao

AU - Joshi, Hrishikesh

AU - Barzilay, Regina

AU - Jaakkola, Tommi

AU - Tymoshenko, Katerina

AU - Moschitti, Alessandro

AU - Marques, Lluis

PY - 2016

Y1 - 2016

N2 - Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).1

AB - Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).1

UR - http://www.scopus.com/inward/record.url?scp=84993660586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84993660586&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1279

EP - 1289

BT - 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -