Joint learning with global inference for comment classification in community question answering

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

14 Citations (Scopus)

Abstract

This paper addresses the problem of comment classification in community Question Answering. Following the state of the art, we approach the task with a global inference process to exploit the information of all comments in the answer-thread in the form of a fully connected graph. Our contribution comprises two novel joint learning models that are on-line and integrate inference within learning. The first one jointly learns two node- and edge-level MaxEnt classifiers with stochastic gradient descent and integrates the inference step with loopy belief propagation. The second model is an instance of fully connected pairwise CRFs (FCCRF). The FCCRF model significantly outperforms all other approaches and yields the best results on the task to date. Crucial elements for its success are the global normalization and an Ising-like edge potential.

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)
Pages703-713
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

learning
community
normalization
Classifiers
Inference
Question Answering
Graph
Normalization
Descent
Classifier
Maximum Entropy
Learning Model

ASJC Scopus subject areas

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

Cite this

Rayhan Joty, S., Marques, L., & Nakov, P. (2016). Joint learning with global inference for comment classification in community question answering. 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. 703-713). Association for Computational Linguistics (ACL).

Joint learning with global inference for comment classification in community question answering. / Rayhan Joty, Shafiq; Marques, Lluis; Nakov, Preslav.

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. 703-713.

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

Rayhan Joty, S, Marques, L & Nakov, P 2016, Joint learning with global inference for comment classification in community question answering. 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. 703-713, 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.
Rayhan Joty S, Marques L, Nakov P. Joint learning with global inference for comment classification in community question answering. 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. 703-713
Rayhan Joty, Shafiq ; Marques, Lluis ; Nakov, Preslav. / Joint learning with global inference for comment classification in community question answering. 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. 703-713
@inproceedings{e988c5c0be974f24a8f11850b03c92e6,
title = "Joint learning with global inference for comment classification in community question answering",
abstract = "This paper addresses the problem of comment classification in community Question Answering. Following the state of the art, we approach the task with a global inference process to exploit the information of all comments in the answer-thread in the form of a fully connected graph. Our contribution comprises two novel joint learning models that are on-line and integrate inference within learning. The first one jointly learns two node- and edge-level MaxEnt classifiers with stochastic gradient descent and integrates the inference step with loopy belief propagation. The second model is an instance of fully connected pairwise CRFs (FCCRF). The FCCRF model significantly outperforms all other approaches and yields the best results on the task to date. Crucial elements for its success are the global normalization and an Ising-like edge potential.",
author = "{Rayhan Joty}, Shafiq and Lluis Marques and Preslav Nakov",
year = "2016",
language = "English",
pages = "703--713",
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 - Joint learning with global inference for comment classification in community question answering

AU - Rayhan Joty, Shafiq

AU - Marques, Lluis

AU - Nakov, Preslav

PY - 2016

Y1 - 2016

N2 - This paper addresses the problem of comment classification in community Question Answering. Following the state of the art, we approach the task with a global inference process to exploit the information of all comments in the answer-thread in the form of a fully connected graph. Our contribution comprises two novel joint learning models that are on-line and integrate inference within learning. The first one jointly learns two node- and edge-level MaxEnt classifiers with stochastic gradient descent and integrates the inference step with loopy belief propagation. The second model is an instance of fully connected pairwise CRFs (FCCRF). The FCCRF model significantly outperforms all other approaches and yields the best results on the task to date. Crucial elements for its success are the global normalization and an Ising-like edge potential.

AB - This paper addresses the problem of comment classification in community Question Answering. Following the state of the art, we approach the task with a global inference process to exploit the information of all comments in the answer-thread in the form of a fully connected graph. Our contribution comprises two novel joint learning models that are on-line and integrate inference within learning. The first one jointly learns two node- and edge-level MaxEnt classifiers with stochastic gradient descent and integrates the inference step with loopy belief propagation. The second model is an instance of fully connected pairwise CRFs (FCCRF). The FCCRF model significantly outperforms all other approaches and yields the best results on the task to date. Crucial elements for its success are the global normalization and an Ising-like edge potential.

UR - http://www.scopus.com/inward/record.url?scp=84994156574&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994156574&partnerID=8YFLogxK

M3 - Conference contribution

SP - 703

EP - 713

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 -