Entity Linking for Web Search Queries

Deepak Padmanabhan, Sayan Ranu, Prithu Banerjee, Sameep Mehta

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

4 Citations (Scopus)

Abstract

We consider the problem of linking web search queries to entities from a knowledge base such as Wikipedia. Such linking enables converting a user’s web search session to a footprint in the knowledge base that could be used to enrich the user profile. Traditional methods for entity linking have been directed towards finding entity mentions in text documents such as news reports, each of which are possibly linked to multiple entities enabling the usage of measures like entity set coherence. Since web search queries are very small text fragments, such criteria that rely on existence of a multitude of mentions do not work too well on them. We propose a three-phase method for linking web search queries to wikipedia entities. The first phase does IR-style scoring of entities against the search query to narrow down to a subset of entities that are expanded using hyperlink information in the second phase to a larger set. Lastly, we use a graph traversal approach to identify the top entities to link the query to. Through an empirical evaluation on real-world web search queries, we illustrate that our methods significantly enhance the linking accuracy over state-of-the-art methods.
LanguageEnglish
Title of host publicationAdvances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.
EditorsAllan Hanbury, Gabriella Kazai, Andreas Rauber, Norbert Fuhr
PublisherSpringer International Publishing Switzerland
Pages394-399
Number of pages6
Volume9022
ISBN (Electronic)9783319163543
ISBN (Print)9783319163536
DOIs
Publication statusPublished - 2015
EventECIR 2015 - Austria, Vienna, Austria
Duration: 29 Mar 201502 Apr 2015

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume9022
ISSN (Print)0302-9743

Conference

ConferenceECIR 2015
CountryAustria
CityVienna
Period29/03/201502/04/2015

Cite this

Padmanabhan, D., Ranu, S., Banerjee, P., & Mehta, S. (2015). Entity Linking for Web Search Queries. In A. Hanbury, G. Kazai, A. Rauber, & N. Fuhr (Eds.), Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings. (Vol. 9022, pp. 394-399). (Lecture Notes in Computer Science; Vol. 9022). Springer International Publishing Switzerland. https://doi.org/10.1007/978-3-319-16354-3_43
Padmanabhan, Deepak ; Ranu, Sayan ; Banerjee, Prithu ; Mehta, Sameep. / Entity Linking for Web Search Queries. Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.. editor / Allan Hanbury ; Gabriella Kazai ; Andreas Rauber ; Norbert Fuhr. Vol. 9022 Springer International Publishing Switzerland, 2015. pp. 394-399 (Lecture Notes in Computer Science).
@inproceedings{84dfcbcb235c41708a562d01a0749ff3,
title = "Entity Linking for Web Search Queries",
abstract = "We consider the problem of linking web search queries to entities from a knowledge base such as Wikipedia. Such linking enables converting a user’s web search session to a footprint in the knowledge base that could be used to enrich the user profile. Traditional methods for entity linking have been directed towards finding entity mentions in text documents such as news reports, each of which are possibly linked to multiple entities enabling the usage of measures like entity set coherence. Since web search queries are very small text fragments, such criteria that rely on existence of a multitude of mentions do not work too well on them. We propose a three-phase method for linking web search queries to wikipedia entities. The first phase does IR-style scoring of entities against the search query to narrow down to a subset of entities that are expanded using hyperlink information in the second phase to a larger set. Lastly, we use a graph traversal approach to identify the top entities to link the query to. Through an empirical evaluation on real-world web search queries, we illustrate that our methods significantly enhance the linking accuracy over state-of-the-art methods.",
author = "Deepak Padmanabhan and Sayan Ranu and Prithu Banerjee and Sameep Mehta",
year = "2015",
doi = "10.1007/978-3-319-16354-3_43",
language = "English",
isbn = "9783319163536",
volume = "9022",
series = "Lecture Notes in Computer Science",
publisher = "Springer International Publishing Switzerland",
pages = "394--399",
editor = "Allan Hanbury and Gabriella Kazai and Andreas Rauber and Norbert Fuhr",
booktitle = "Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.",

}

Padmanabhan, D, Ranu, S, Banerjee, P & Mehta, S 2015, Entity Linking for Web Search Queries. in A Hanbury, G Kazai, A Rauber & N Fuhr (eds), Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.. vol. 9022, Lecture Notes in Computer Science, vol. 9022, Springer International Publishing Switzerland, pp. 394-399, ECIR 2015, Vienna, Austria, 29/03/2015. https://doi.org/10.1007/978-3-319-16354-3_43

Entity Linking for Web Search Queries. / Padmanabhan, Deepak; Ranu, Sayan; Banerjee, Prithu; Mehta, Sameep.

Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.. ed. / Allan Hanbury; Gabriella Kazai; Andreas Rauber; Norbert Fuhr. Vol. 9022 Springer International Publishing Switzerland, 2015. p. 394-399 (Lecture Notes in Computer Science; Vol. 9022).

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

TY - GEN

T1 - Entity Linking for Web Search Queries

AU - Padmanabhan, Deepak

AU - Ranu, Sayan

AU - Banerjee, Prithu

AU - Mehta, Sameep

PY - 2015

Y1 - 2015

N2 - We consider the problem of linking web search queries to entities from a knowledge base such as Wikipedia. Such linking enables converting a user’s web search session to a footprint in the knowledge base that could be used to enrich the user profile. Traditional methods for entity linking have been directed towards finding entity mentions in text documents such as news reports, each of which are possibly linked to multiple entities enabling the usage of measures like entity set coherence. Since web search queries are very small text fragments, such criteria that rely on existence of a multitude of mentions do not work too well on them. We propose a three-phase method for linking web search queries to wikipedia entities. The first phase does IR-style scoring of entities against the search query to narrow down to a subset of entities that are expanded using hyperlink information in the second phase to a larger set. Lastly, we use a graph traversal approach to identify the top entities to link the query to. Through an empirical evaluation on real-world web search queries, we illustrate that our methods significantly enhance the linking accuracy over state-of-the-art methods.

AB - We consider the problem of linking web search queries to entities from a knowledge base such as Wikipedia. Such linking enables converting a user’s web search session to a footprint in the knowledge base that could be used to enrich the user profile. Traditional methods for entity linking have been directed towards finding entity mentions in text documents such as news reports, each of which are possibly linked to multiple entities enabling the usage of measures like entity set coherence. Since web search queries are very small text fragments, such criteria that rely on existence of a multitude of mentions do not work too well on them. We propose a three-phase method for linking web search queries to wikipedia entities. The first phase does IR-style scoring of entities against the search query to narrow down to a subset of entities that are expanded using hyperlink information in the second phase to a larger set. Lastly, we use a graph traversal approach to identify the top entities to link the query to. Through an empirical evaluation on real-world web search queries, we illustrate that our methods significantly enhance the linking accuracy over state-of-the-art methods.

U2 - 10.1007/978-3-319-16354-3_43

DO - 10.1007/978-3-319-16354-3_43

M3 - Conference contribution

SN - 9783319163536

VL - 9022

T3 - Lecture Notes in Computer Science

SP - 394

EP - 399

BT - Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.

A2 - Hanbury, Allan

A2 - Kazai, Gabriella

A2 - Rauber, Andreas

A2 - Fuhr, Norbert

PB - Springer International Publishing Switzerland

ER -

Padmanabhan D, Ranu S, Banerjee P, Mehta S. Entity Linking for Web Search Queries. In Hanbury A, Kazai G, Rauber A, Fuhr N, editors, Advances in Information Retrieval: 37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings.. Vol. 9022. Springer International Publishing Switzerland. 2015. p. 394-399. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-16354-3_43