Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents

Rabah A. Al-Zaidy; Cornelia Caragea; C. Lee Giles

doi:10.1145/3308558.3313642

Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents

Rabah A. Al-Zaidy
, Cornelia Caragea
, C. Lee Giles

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

178 Scopus citations

Abstract

In this paper, we address the keyphrase extraction problem as sequence labeling and propose a model that jointly exploits the complementary strengths of Conditional Random Fields that capture label dependencies through a transition parameter matrix consisting of the transition probabilities from one label to the neighboring label, and Bidirectional Long Short Term Memory networks that capture hidden semantics in text through the long distance dependencies. Our results on three datasets of scholarly documents show that the proposed model substantially outperforms strong baselines and previous approaches for keyphrase extraction.

Original language	English
Title of host publication	The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
Publisher	Association for Computing Machinery, Inc
Pages	2551-2557
Number of pages	7
ISBN (Electronic)	9781450366748
DOIs	https://doi.org/10.1145/3308558.3313642
State	Published - 13 May 2019
Externally published	Yes
Event	2019 World Wide Web Conference, WWW 2019 - San Francisco, United States Duration: 13 May 2019 → 17 May 2019

Publication series

Name	The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

Conference

Conference	2019 World Wide Web Conference, WWW 2019
Country/Territory	United States
City	San Francisco
Period	13/05/19 → 17/05/19

Bibliographical note

Publisher Copyright:
© 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License.

Keywords

Deep learning
Keyphrase extraction
Sequence labeling

ASJC Scopus subject areas

Computer Networks and Communications
Software

Access to Document

10.1145/3308558.3313642

Cite this

Al-Zaidy, R. A., Caragea, C., & Lee Giles, C. (2019). Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (pp. 2551-2557). (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308558.3313642

@inproceedings{5ae798aace6f4a37821583125c331eae,

title = "Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents",

abstract = "In this paper, we address the keyphrase extraction problem as sequence labeling and propose a model that jointly exploits the complementary strengths of Conditional Random Fields that capture label dependencies through a transition parameter matrix consisting of the transition probabilities from one label to the neighboring label, and Bidirectional Long Short Term Memory networks that capture hidden semantics in text through the long distance dependencies. Our results on three datasets of scholarly documents show that the proposed model substantially outperforms strong baselines and previous approaches for keyphrase extraction.",

keywords = "Deep learning, Keyphrase extraction, Sequence labeling",

author = "Al-Zaidy, \{Rabah A.\} and Cornelia Caragea and \{Lee Giles\}, C.",

note = "Publisher Copyright: {\textcopyright} 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License.; 2019 World Wide Web Conference, WWW 2019 ; Conference date: 13-05-2019 Through 17-05-2019",

year = "2019",

month = may,

day = "13",

doi = "10.1145/3308558.3313642",

language = "English",

series = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",

publisher = "Association for Computing Machinery, Inc",

pages = "2551--2557",

booktitle = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",

}

Al-Zaidy, RA, Caragea, C & Lee Giles, C 2019, Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents. in The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, Association for Computing Machinery, Inc, pp. 2551-2557, 2019 World Wide Web Conference, WWW 2019, San Francisco, United States, 13/05/19. https://doi.org/10.1145/3308558.3313642

Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents. / Al-Zaidy, Rabah A.; Caragea, Cornelia; Lee Giles, C.
The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 2551-2557 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).

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

TY - GEN

T1 - Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents

AU - Al-Zaidy, Rabah A.

AU - Caragea, Cornelia

AU - Lee Giles, C.

PY - 2019/5/13

Y1 - 2019/5/13

N2 - In this paper, we address the keyphrase extraction problem as sequence labeling and propose a model that jointly exploits the complementary strengths of Conditional Random Fields that capture label dependencies through a transition parameter matrix consisting of the transition probabilities from one label to the neighboring label, and Bidirectional Long Short Term Memory networks that capture hidden semantics in text through the long distance dependencies. Our results on three datasets of scholarly documents show that the proposed model substantially outperforms strong baselines and previous approaches for keyphrase extraction.

AB - In this paper, we address the keyphrase extraction problem as sequence labeling and propose a model that jointly exploits the complementary strengths of Conditional Random Fields that capture label dependencies through a transition parameter matrix consisting of the transition probabilities from one label to the neighboring label, and Bidirectional Long Short Term Memory networks that capture hidden semantics in text through the long distance dependencies. Our results on three datasets of scholarly documents show that the proposed model substantially outperforms strong baselines and previous approaches for keyphrase extraction.

KW - Deep learning

KW - Keyphrase extraction

KW - Sequence labeling

UR - https://www.scopus.com/pages/publications/85066915412

U2 - 10.1145/3308558.3313642

DO - 10.1145/3308558.3313642

M3 - Conference contribution

AN - SCOPUS:85066915412

T3 - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

SP - 2551

EP - 2557

BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

PB - Association for Computing Machinery, Inc

T2 - 2019 World Wide Web Conference, WWW 2019

Y2 - 13 May 2019 through 17 May 2019

ER -

Al-Zaidy RA, Caragea C, Lee Giles C. Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc. 2019. p. 2551-2557. (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). doi: 10.1145/3308558.3313642

Bi-LSTM-CRF sequence labeling for keyphrase extraction from scholarly documents

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this