Learning a deep hybrid model for semi-supervised text classification

Alexander G. Ororbia; C. Lee Giles; David Reitter

Learning a deep hybrid model for semi-supervised text classification

Alexander G. Ororbia, C. Lee Giles, David Reitter

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present a novel fine-tuning algorithm in a deep hybrid architecture for semisupervised text classification. During each increment of the online learning process, the fine-tuning algorithm serves as a top-down mechanism for pseudo-jointly modifying model parameters following a bottom-up generative learning pass. The resulting model, trained under what we call the Bottom-Up-Top-Down learning algorithm, is shown to outperform a variety of competitive models and baselines trained across a wide range of splits between supervised and unsupervised training data.

Original language	English (US)
Title of host publication	Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing
Publisher	Association for Computational Linguistics (ACL)
Pages	471-481
Number of pages	11
ISBN (Electronic)	9781941643327
State	Published - 2015
Event	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal Duration: Sep 17 2015 → Sep 21 2015

Other

Other	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Country/Territory	Portugal
City	Lisbon
Period	9/17/15 → 9/21/15

All Science Journal Classification (ASJC) codes

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Cite this

@inproceedings{e7c8da9f59344892bb4b3ffeeb6d3fc6,

title = "Learning a deep hybrid model for semi-supervised text classification",

abstract = "We present a novel fine-tuning algorithm in a deep hybrid architecture for semisupervised text classification. During each increment of the online learning process, the fine-tuning algorithm serves as a top-down mechanism for pseudo-jointly modifying model parameters following a bottom-up generative learning pass. The resulting model, trained under what we call the Bottom-Up-Top-Down learning algorithm, is shown to outperform a variety of competitive models and baselines trained across a wide range of splits between supervised and unsupervised training data.",

author = "Ororbia, {Alexander G.} and Giles, {C. Lee} and David Reitter",

year = "2015",

language = "English (US)",

pages = "471--481",

booktitle = "Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing",

publisher = "Association for Computational Linguistics (ACL)",

note = "Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 ; Conference date: 17-09-2015 Through 21-09-2015",

}

Ororbia, AG, Giles, CL & Reitter, D 2015, Learning a deep hybrid model for semi-supervised text classification. in Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), pp. 471-481, Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 9/17/15.

Learning a deep hybrid model for semi-supervised text classification. / Ororbia, Alexander G.; Giles, C. Lee; Reitter, David.
Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2015. p. 471-481.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Learning a deep hybrid model for semi-supervised text classification

AU - Ororbia, Alexander G.

AU - Giles, C. Lee

AU - Reitter, David

PY - 2015

Y1 - 2015

N2 - We present a novel fine-tuning algorithm in a deep hybrid architecture for semisupervised text classification. During each increment of the online learning process, the fine-tuning algorithm serves as a top-down mechanism for pseudo-jointly modifying model parameters following a bottom-up generative learning pass. The resulting model, trained under what we call the Bottom-Up-Top-Down learning algorithm, is shown to outperform a variety of competitive models and baselines trained across a wide range of splits between supervised and unsupervised training data.

AB - We present a novel fine-tuning algorithm in a deep hybrid architecture for semisupervised text classification. During each increment of the online learning process, the fine-tuning algorithm serves as a top-down mechanism for pseudo-jointly modifying model parameters following a bottom-up generative learning pass. The resulting model, trained under what we call the Bottom-Up-Top-Down learning algorithm, is shown to outperform a variety of competitive models and baselines trained across a wide range of splits between supervised and unsupervised training data.

UR - http://www.scopus.com/inward/record.url?scp=84959885794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959885794&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84959885794

SP - 471

EP - 481

BT - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics (ACL)

T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015

Y2 - 17 September 2015 through 21 September 2015

ER -

Learning a deep hybrid model for semi-supervised text classification

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this