Lifelong learning for sentiment classification

Zhiyuan Chen; Nianzu Ma; Bing Liu

doi:10.3115/v1/p15-2123

Lifelong learning for sentiment classification

Zhiyuan Chen, Nianzu Ma, Bing Liu

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

101 Scopus citations

Abstract

This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this paper, we first discuss LL in general and then LL for sentiment classification in particular. The proposed LL approach adopts a Bayesian optimization framework based on stochastic gradient descent. Our experimental results show that the proposed method outperforms baseline methods significantly, which demonstrates that lifelong learning is a promising research direction.

Original language	English (US)
Title of host publication	ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	750-756
Number of pages	7
ISBN (Electronic)	9781941643730
DOIs	https://doi.org/10.3115/v1/p15-2123
State	Published - 2015
Externally published	Yes
Event	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China Duration: Jul 26 2015 → Jul 31 2015

Publication series

Name	ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Volume	2

Conference

Conference	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
Country/Territory	China
City	Beijing
Period	7/26/15 → 7/31/15

Bibliographical note

Publisher Copyright:
© 2015 Association for Computational Linguistics.

Publisher link

10.3115/v1/p15-2123

Find It

Find It at U of M Libraries

Cite this

Chen, Z., Ma, N., & Liu, B. (2015). Lifelong learning for sentiment classification. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (pp. 750-756). (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference; Vol. 2). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p15-2123

Lifelong learning for sentiment classification. / Chen, Zhiyuan; Ma, Nianzu; Liu, Bing.
ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. p. 750-756 (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference; Vol. 2).

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

Chen, Z, Ma, N & Liu, B 2015, Lifelong learning for sentiment classification. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference, vol. 2, Association for Computational Linguistics (ACL), pp. 750-756, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 7/26/15. https://doi.org/10.3115/v1/p15-2123

Chen Z, Ma N, Liu B. Lifelong learning for sentiment classification. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2015. p. 750-756. (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference). doi: 10.3115/v1/p15-2123

Chen, Zhiyuan ; Ma, Nianzu ; Liu, Bing. / Lifelong learning for sentiment classification. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. pp. 750-756 (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference).

@inproceedings{4d4ef1d516b5447da042c39d2519ac74,

title = "Lifelong learning for sentiment classification",

abstract = "This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this paper, we first discuss LL in general and then LL for sentiment classification in particular. The proposed LL approach adopts a Bayesian optimization framework based on stochastic gradient descent. Our experimental results show that the proposed method outperforms baseline methods significantly, which demonstrates that lifelong learning is a promising research direction.",

author = "Zhiyuan Chen and Nianzu Ma and Bing Liu",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 ; Conference date: 26-07-2015 Through 31-07-2015",

year = "2015",

doi = "10.3115/v1/p15-2123",

language = "English (US)",

series = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",

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

pages = "750--756",

booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - Lifelong learning for sentiment classification

AU - Chen, Zhiyuan

AU - Ma, Nianzu

AU - Liu, Bing

PY - 2015

Y1 - 2015

N2 - This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this paper, we first discuss LL in general and then LL for sentiment classification in particular. The proposed LL approach adopts a Bayesian optimization framework based on stochastic gradient descent. Our experimental results show that the proposed method outperforms baseline methods significantly, which demonstrates that lifelong learning is a promising research direction.

AB - This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this paper, we first discuss LL in general and then LL for sentiment classification in particular. The proposed LL approach adopts a Bayesian optimization framework based on stochastic gradient descent. Our experimental results show that the proposed method outperforms baseline methods significantly, which demonstrates that lifelong learning is a promising research direction.

UR - http://www.scopus.com/inward/record.url?scp=84944070119&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944070119&partnerID=8YFLogxK

U2 - 10.3115/v1/p15-2123

DO - 10.3115/v1/p15-2123

M3 - Conference contribution

AN - SCOPUS:84944070119

T3 - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

SP - 750

EP - 756

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015

Y2 - 26 July 2015 through 31 July 2015

ER -

Lifelong learning for sentiment classification

Abstract

Publication series

Conference

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this