Web Document Encoding for Structure-Aware Keyphrase Extraction

Jihyuk Kim; Young In Song; Seung Won Hwang

doi:10.1145/3404835.3463067

Web Document Encoding for Structure-Aware Keyphrase Extraction

Jihyuk Kim, Young In Song, Seung Won Hwang

College of Computing

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

3 Citations (Scopus)

Abstract

We study keyphrase extraction (KPE) from Web documents. Our key contribution is encoding Web documents to leverage structure, such as title or anchors, by building a graph of words representing both (a) position-based proximity and (b) structural relations. We evaluate KPE performance on real-world search engine NAVER and human-annotated KPE benchmarks, and ours outperforms state-of-the-arts in both tasks.

Original language	English
Title of host publication	SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher	Association for Computing Machinery, Inc
Pages	1823-1827
Number of pages	5
ISBN (Electronic)	9781450380379
DOIs	https://doi.org/10.1145/3404835.3463067
Publication status	Published - 2021 Jul 11
Event	44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021 - Virtual, Online, Canada Duration: 2021 Jul 11 → 2021 Jul 15

Publication series

Name	SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference	44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021
Country/Territory	Canada
City	Virtual, Online
Period	21/7/11 → 21/7/15

Bibliographical note

Funding Information:
This work was supported by NAVER-SQR program from NAVER corporation, and IITP funded by MSIT (No. 2017-0-01779, XAI).

Publisher Copyright:
© 2021 ACM.

All Science Journal Classification (ASJC) codes

Software
Computer Graphics and Computer-Aided Design
Information Systems

Access to Document

10.1145/3404835.3463067

Cite this

Kim, J., Song, Y. I., & Hwang, S. W. (2021). Web Document Encoding for Structure-Aware Keyphrase Extraction. In SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1823-1827). [3463067] (SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval). Association for Computing Machinery, Inc. https://doi.org/10.1145/3404835.3463067

Kim, Jihyuk ; Song, Young In ; Hwang, Seung Won. / Web Document Encoding for Structure-Aware Keyphrase Extraction. SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2021. pp. 1823-1827 (SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval).

@inproceedings{bbbe3aeaeda847d1811e0f870009fadf,

title = "Web Document Encoding for Structure-Aware Keyphrase Extraction",

abstract = "We study keyphrase extraction (KPE) from Web documents. Our key contribution is encoding Web documents to leverage structure, such as title or anchors, by building a graph of words representing both (a) position-based proximity and (b) structural relations. We evaluate KPE performance on real-world search engine NAVER and human-annotated KPE benchmarks, and ours outperforms state-of-the-arts in both tasks.",

author = "Jihyuk Kim and Song, {Young In} and Hwang, {Seung Won}",

note = "Funding Information: This work was supported by NAVER-SQR program from NAVER corporation, and IITP funded by MSIT (No. 2017-0-01779, XAI). Publisher Copyright: {\textcopyright} 2021 ACM.; 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021 ; Conference date: 11-07-2021 Through 15-07-2021",

year = "2021",

month = jul,

day = "11",

doi = "10.1145/3404835.3463067",

language = "English",

series = "SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval",

publisher = "Association for Computing Machinery, Inc",

pages = "1823--1827",

booktitle = "SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

Kim, J, Song, YI & Hwang, SW 2021, Web Document Encoding for Structure-Aware Keyphrase Extraction. in SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval., 3463067, SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, pp. 1823-1827, 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021, Virtual, Online, Canada, 21/7/11. https://doi.org/10.1145/3404835.3463067

Web Document Encoding for Structure-Aware Keyphrase Extraction. / Kim, Jihyuk; Song, Young In; Hwang, Seung Won.

SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2021. p. 1823-1827 3463067 (SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval).

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

TY - GEN

T1 - Web Document Encoding for Structure-Aware Keyphrase Extraction

AU - Kim, Jihyuk

AU - Song, Young In

AU - Hwang, Seung Won

PY - 2021/7/11

Y1 - 2021/7/11

N2 - We study keyphrase extraction (KPE) from Web documents. Our key contribution is encoding Web documents to leverage structure, such as title or anchors, by building a graph of words representing both (a) position-based proximity and (b) structural relations. We evaluate KPE performance on real-world search engine NAVER and human-annotated KPE benchmarks, and ours outperforms state-of-the-arts in both tasks.

AB - We study keyphrase extraction (KPE) from Web documents. Our key contribution is encoding Web documents to leverage structure, such as title or anchors, by building a graph of words representing both (a) position-based proximity and (b) structural relations. We evaluate KPE performance on real-world search engine NAVER and human-annotated KPE benchmarks, and ours outperforms state-of-the-arts in both tasks.

UR - http://www.scopus.com/inward/record.url?scp=85111696686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85111696686&partnerID=8YFLogxK

U2 - 10.1145/3404835.3463067

DO - 10.1145/3404835.3463067

M3 - Conference contribution

AN - SCOPUS:85111696686

T3 - SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

SP - 1823

EP - 1827

BT - SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

PB - Association for Computing Machinery, Inc

T2 - 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021

Y2 - 11 July 2021 through 15 July 2021

ER -

Kim J, Song YI, Hwang SW. Web Document Encoding for Structure-Aware Keyphrase Extraction. In SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc. 2021. p. 1823-1827. 3463067. (SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval). doi: 10.1145/3404835.3463067

Web Document Encoding for Structure-Aware Keyphrase Extraction

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this