Reinforcing the topic of embeddings with Theta Pure Dependence for text classification

Ning Xing; Yuexian Hou; Peng Zhang; Wenjie Li; Dawei Song

Reinforcing the topic of embeddings with Theta Pure Dependence for text classification

Ning Xing, Yuexian Hou, Peng Zhang, Wenjie Li, Dawei Song

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

For sentiment classification, it is often recognized that embedding based on distributional hypothesis is weak in capturing sentiment contrast-contrasting words may have similar local context. Based on broader context, we propose to incorporate Theta Pure Dependence (TPD) into the Paragraph Vector method to reinforce topical and sentimental information. TPD has a theoretical guarantee that the word dependency is pure, i.e., the dependence pattern has the integral meaning whose underlying distribution can not be conditionally factorized. Our method outperforms the state-of-the-art performance on text classification tasks.

Original language	English
Title of host publication	Conference Proceedings - EMNLP 2015
Subtitle of host publication	Conference on Empirical Methods in Natural Language Processing
Publisher	Association for Computational Linguistics (ACL)
Pages	2551-2556
Number of pages	6
ISBN (Electronic)	9781941643327
Publication status	Published - 1 Jan 2015
Event	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal Duration: 17 Sept 2015 → 21 Sept 2015

Conference

Conference	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → 21/09/15

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Cite this

@inproceedings{61c87cf50ac44a26b6d6ecf0eb643f3a,

title = "Reinforcing the topic of embeddings with Theta Pure Dependence for text classification",

abstract = "For sentiment classification, it is often recognized that embedding based on distributional hypothesis is weak in capturing sentiment contrast-contrasting words may have similar local context. Based on broader context, we propose to incorporate Theta Pure Dependence (TPD) into the Paragraph Vector method to reinforce topical and sentimental information. TPD has a theoretical guarantee that the word dependency is pure, i.e., the dependence pattern has the integral meaning whose underlying distribution can not be conditionally factorized. Our method outperforms the state-of-the-art performance on text classification tasks.",

author = "Ning Xing and Yuexian Hou and Peng Zhang and Wenjie Li and Dawei Song",

year = "2015",

month = jan,

day = "1",

language = "English",

pages = "2551--2556",

booktitle = "Conference Proceedings - EMNLP 2015",

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",

}

Xing, N, Hou, Y, Zhang, P, Li, W & Song, D 2015, Reinforcing the topic of embeddings with Theta Pure Dependence for text classification. in Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), pp. 2551-2556, Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 17/09/15.

Reinforcing the topic of embeddings with Theta Pure Dependence for text classification. / Xing, Ning; Hou, Yuexian; Zhang, Peng et al.
Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2015. p. 2551-2556.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Reinforcing the topic of embeddings with Theta Pure Dependence for text classification

AU - Xing, Ning

AU - Hou, Yuexian

AU - Zhang, Peng

AU - Li, Wenjie

AU - Song, Dawei

PY - 2015/1/1

Y1 - 2015/1/1

N2 - For sentiment classification, it is often recognized that embedding based on distributional hypothesis is weak in capturing sentiment contrast-contrasting words may have similar local context. Based on broader context, we propose to incorporate Theta Pure Dependence (TPD) into the Paragraph Vector method to reinforce topical and sentimental information. TPD has a theoretical guarantee that the word dependency is pure, i.e., the dependence pattern has the integral meaning whose underlying distribution can not be conditionally factorized. Our method outperforms the state-of-the-art performance on text classification tasks.

AB - For sentiment classification, it is often recognized that embedding based on distributional hypothesis is weak in capturing sentiment contrast-contrasting words may have similar local context. Based on broader context, we propose to incorporate Theta Pure Dependence (TPD) into the Paragraph Vector method to reinforce topical and sentimental information. TPD has a theoretical guarantee that the word dependency is pure, i.e., the dependence pattern has the integral meaning whose underlying distribution can not be conditionally factorized. Our method outperforms the state-of-the-art performance on text classification tasks.

UR - http://www.scopus.com/inward/record.url?scp=84959926529&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 2551

EP - 2556

BT - Conference Proceedings - EMNLP 2015

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 -

Reinforcing the topic of embeddings with Theta Pure Dependence for text classification

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this