Grouping business news stories based on salience of named entities

Llorenc Escoter; Lidia Pivovarova; Mian Du; Anisia Katinskaia; Roman Yangarber

doi:10.18653/v1/e17-1103

Grouping business news stories based on salience of named entities

Llorenc Escoter, Lidia Pivovarova, Mian Du, Anisia Katinskaia, Roman Yangarber

Department of Computer Science

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

Abstract

In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user—reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience—a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus of
business news stories.

Original language	English
Title of host publication	15th Conference of the European Chapter of the Association for Computational Linguistics : Proceedings of Conference, Volume 1: Long Papers
Number of pages	11
Place of Publication	Stroudsburg, PA
Publisher	The Association for Computational Linguistics
Publication date	2017
Pages	1096-1106
ISBN (Electronic)	978-1-945626-34-0
DOIs	https://doi.org/10.18653/v1/e17-1103
Publication status	Published - 2017
MoE publication type	A4 Article in conference proceedings
Event	Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017 Conference number: 15

Fields of Science

113 Computer and information sciences

Access to Document

10.18653/v1/e17-1103

2017-eacl-grouping

Cite this

Escoter, L., Pivovarova, L., Du, M., Katinskaia, A., & Yangarber, R. (2017). Grouping business news stories based on salience of named entities. In 15th Conference of the European Chapter of the Association for Computational Linguistics: Proceedings of Conference, Volume 1: Long Papers (pp. 1096-1106). The Association for Computational Linguistics. https://doi.org/10.18653/v1/e17-1103

@inproceedings{5a461571388346838dd4c33028b0d79f,

title = "Grouping business news stories based on salience of named entities",

abstract = "In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user—reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience—a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus ofbusiness news stories.",

keywords = "113 Computer and information sciences",

author = "Llorenc Escoter and Lidia Pivovarova and Mian Du and Anisia Katinskaia and Roman Yangarber",

year = "2017",

doi = "10.18653/v1/e17-1103",

language = "English",

pages = "1096--1106",

booktitle = "15th Conference of the European Chapter of the Association for Computational Linguistics",

publisher = "The Association for Computational Linguistics",

address = "United States",

note = "Conference of the European Chapter of the Association for Computational Linguistics ; Conference date: 03-04-2017 Through 07-04-2017",

}

Escoter, L, Pivovarova, L, Du, M, Katinskaia, A & Yangarber, R 2017, Grouping business news stories based on salience of named entities. in 15th Conference of the European Chapter of the Association for Computational Linguistics: Proceedings of Conference, Volume 1: Long Papers. The Association for Computational Linguistics, Stroudsburg, PA, pp. 1096-1106, Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 03/04/2017. https://doi.org/10.18653/v1/e17-1103

Grouping business news stories based on salience of named entities. / Escoter, Llorenc; Pivovarova, Lidia; Du, Mian et al.
15th Conference of the European Chapter of the Association for Computational Linguistics: Proceedings of Conference, Volume 1: Long Papers. Stroudsburg, PA: The Association for Computational Linguistics, 2017. p. 1096-1106.

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

TY - GEN

T1 - Grouping business news stories based on salience of named entities

AU - Escoter, Llorenc

AU - Pivovarova, Lidia

AU - Du, Mian

AU - Katinskaia, Anisia

AU - Yangarber, Roman

N1 - Conference code: 15

PY - 2017

Y1 - 2017

N2 - In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user—reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience—a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus ofbusiness news stories.

AB - In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user—reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience—a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus ofbusiness news stories.

KW - 113 Computer and information sciences

UR - http://eacl2017.org

U2 - 10.18653/v1/e17-1103

DO - 10.18653/v1/e17-1103

M3 - Conference contribution

SP - 1096

EP - 1106

BT - 15th Conference of the European Chapter of the Association for Computational Linguistics

PB - The Association for Computational Linguistics

CY - Stroudsburg, PA

T2 - Conference of the European Chapter of the Association for Computational Linguistics

Y2 - 3 April 2017 through 7 April 2017

ER -

Escoter L, Pivovarova L, Du M, Katinskaia A , Yangarber R. Grouping business news stories based on salience of named entities. In 15th Conference of the European Chapter of the Association for Computational Linguistics: Proceedings of Conference, Volume 1: Long Papers. Stroudsburg, PA: The Association for Computational Linguistics. 2017. p. 1096-1106 doi: 10.18653/v1/e17-1103

Grouping business news stories based on salience of named entities

Abstract

Fields of Science

Access to Document

Other files and links

LLL: Language Learning Lab

Cite this

Grouping business news stories based on salience of named entities

Abstract

Fields of Science

Access to Document

Other files and links

Projects

LLL: Language Learning Lab

Cite this