Evaluating the helpfulness of linked entities to readers

Ikuyai Yamada, Tomotaka Ito, Shinnosuke Usami, Shinsuke Takagi, Hideaki Takeda, Yoshiyasu Takefuji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

When we encounter an interesting entity (e.g., a person's name or a geographic location) while reading text, we typically search and retrieve relevant information about it. Entity linking (EL) is the task of linking entities in a text to the corresponding entries in a knowledge base, such as Wikipedia. Recently, EL has received considerable attention. EL can be used to enhance a user's text reading experience by streamlining the process of retrieving information on entities. Several EL methods have been proposed, though they tend to extract all of the entities in a document including unnecessary ones for users. Excessive linking of entities can be distracting and degrade the user experience. In this paper, we propose a new method for evaluating the helpfulness of linking entities to users. We address this task using supervised machine-learning with a broad set of features. Experimental results show that our method significantly outperforms baseline methods by approximately 5.7%-12% F1. In addition, we propose an application, Linkify, which enables developers to integrate EL easily into their web sites.

Original languageEnglish
Title of host publicationHT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery
Pages169-178
Number of pages10
ISBN (Print)9781450329545
DOIs
Publication statusPublished - 2014
Event25th ACM Conference on Hypertext and Social Media, HT 2014 - Santiago, Chile
Duration: 2014 Sep 12014 Sep 4

Other

Other25th ACM Conference on Hypertext and Social Media, HT 2014
CountryChile
CitySantiago
Period14/9/114/9/4

Fingerprint

Learning systems
Websites

Keywords

  • entity linking
  • knowledge base
  • wikipedia

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Yamada, I., Ito, T., Usami, S., Takagi, S., Takeda, H., & Takefuji, Y. (2014). Evaluating the helpfulness of linked entities to readers. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media (pp. 169-178). Association for Computing Machinery. https://doi.org/10.1145/2631775.2631802

Evaluating the helpfulness of linked entities to readers. / Yamada, Ikuyai; Ito, Tomotaka; Usami, Shinnosuke; Takagi, Shinsuke; Takeda, Hideaki; Takefuji, Yoshiyasu.

HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, 2014. p. 169-178.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamada, I, Ito, T, Usami, S, Takagi, S, Takeda, H & Takefuji, Y 2014, Evaluating the helpfulness of linked entities to readers. in HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, pp. 169-178, 25th ACM Conference on Hypertext and Social Media, HT 2014, Santiago, Chile, 14/9/1. https://doi.org/10.1145/2631775.2631802
Yamada I, Ito T, Usami S, Takagi S, Takeda H, Takefuji Y. Evaluating the helpfulness of linked entities to readers. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery. 2014. p. 169-178 https://doi.org/10.1145/2631775.2631802
Yamada, Ikuyai ; Ito, Tomotaka ; Usami, Shinnosuke ; Takagi, Shinsuke ; Takeda, Hideaki ; Takefuji, Yoshiyasu. / Evaluating the helpfulness of linked entities to readers. HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, 2014. pp. 169-178
@inproceedings{de7a37d3433b41679efe5c742f42b621,
title = "Evaluating the helpfulness of linked entities to readers",
abstract = "When we encounter an interesting entity (e.g., a person's name or a geographic location) while reading text, we typically search and retrieve relevant information about it. Entity linking (EL) is the task of linking entities in a text to the corresponding entries in a knowledge base, such as Wikipedia. Recently, EL has received considerable attention. EL can be used to enhance a user's text reading experience by streamlining the process of retrieving information on entities. Several EL methods have been proposed, though they tend to extract all of the entities in a document including unnecessary ones for users. Excessive linking of entities can be distracting and degrade the user experience. In this paper, we propose a new method for evaluating the helpfulness of linking entities to users. We address this task using supervised machine-learning with a broad set of features. Experimental results show that our method significantly outperforms baseline methods by approximately 5.7{\%}-12{\%} F1. In addition, we propose an application, Linkify, which enables developers to integrate EL easily into their web sites.",
keywords = "entity linking, knowledge base, wikipedia",
author = "Ikuyai Yamada and Tomotaka Ito and Shinnosuke Usami and Shinsuke Takagi and Hideaki Takeda and Yoshiyasu Takefuji",
year = "2014",
doi = "10.1145/2631775.2631802",
language = "English",
isbn = "9781450329545",
pages = "169--178",
booktitle = "HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Evaluating the helpfulness of linked entities to readers

AU - Yamada, Ikuyai

AU - Ito, Tomotaka

AU - Usami, Shinnosuke

AU - Takagi, Shinsuke

AU - Takeda, Hideaki

AU - Takefuji, Yoshiyasu

PY - 2014

Y1 - 2014

N2 - When we encounter an interesting entity (e.g., a person's name or a geographic location) while reading text, we typically search and retrieve relevant information about it. Entity linking (EL) is the task of linking entities in a text to the corresponding entries in a knowledge base, such as Wikipedia. Recently, EL has received considerable attention. EL can be used to enhance a user's text reading experience by streamlining the process of retrieving information on entities. Several EL methods have been proposed, though they tend to extract all of the entities in a document including unnecessary ones for users. Excessive linking of entities can be distracting and degrade the user experience. In this paper, we propose a new method for evaluating the helpfulness of linking entities to users. We address this task using supervised machine-learning with a broad set of features. Experimental results show that our method significantly outperforms baseline methods by approximately 5.7%-12% F1. In addition, we propose an application, Linkify, which enables developers to integrate EL easily into their web sites.

AB - When we encounter an interesting entity (e.g., a person's name or a geographic location) while reading text, we typically search and retrieve relevant information about it. Entity linking (EL) is the task of linking entities in a text to the corresponding entries in a knowledge base, such as Wikipedia. Recently, EL has received considerable attention. EL can be used to enhance a user's text reading experience by streamlining the process of retrieving information on entities. Several EL methods have been proposed, though they tend to extract all of the entities in a document including unnecessary ones for users. Excessive linking of entities can be distracting and degrade the user experience. In this paper, we propose a new method for evaluating the helpfulness of linking entities to users. We address this task using supervised machine-learning with a broad set of features. Experimental results show that our method significantly outperforms baseline methods by approximately 5.7%-12% F1. In addition, we propose an application, Linkify, which enables developers to integrate EL easily into their web sites.

KW - entity linking

KW - knowledge base

KW - wikipedia

UR - http://www.scopus.com/inward/record.url?scp=84907384181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907384181&partnerID=8YFLogxK

U2 - 10.1145/2631775.2631802

DO - 10.1145/2631775.2631802

M3 - Conference contribution

AN - SCOPUS:84907384181

SN - 9781450329545

SP - 169

EP - 178

BT - HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery

ER -