Snippet-based relevance predictions for federated web search

Thomas Demeester; Dong-Phuong Nguyen; Rudolf Berend Trieschnigg; Chris Develder; Djoerd Hiemstra

doi:10.1007/978-3-642-36973-5_63

Snippet-based relevance predictions for federated web search

Thomas Demeester, Dong-Phuong Nguyen, Rudolf Berend Trieschnigg, Chris Develder, Djoerd Hiemstra

Databases (Former)

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

7 Citations (Scopus)

57 Downloads (Pure)

Abstract

How well can the relevance of a page be predicted, purely based on snippets? This would be highly useful in a Federated Web Search setting where caching large amounts of result snippets is more feasible than caching entire pages. The experiments reported in this paper make use of result snippets and pages from a diverse set of actual Web search engines. A linear classifier is trained to predict the snippet-based user estimate of page relevance, but also, to predict the actual page relevance, again based on snippets alone. The presented results confirm the validity of the proposed approach and provide promising insights into future result merging strategies for a Federated Web Search setting.

Original language	Undefined
Title of host publication	Advances in Information Retrieval, Proceedings of the 35th European Conference on IR Research, ECIR 2013
Place of Publication	Berlin
Publisher	Springer
Pages	697-700
Number of pages	4
ISBN (Print)	978-3-642-36972-8
DOIs	https://doi.org/10.1007/978-3-642-36973-5_63
Publication status	Published - Mar 2013
Event	35th European Conference on Information Retrieval, ECIR 2013: (IR Resarch) - Moscow, Russian Federation Duration: 24 Mar 2013 → 27 Mar 2013 Conference number: 35

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	7814
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	35th European Conference on Information Retrieval, ECIR 2013
Abbreviated title	ECIR
Country/Territory	Russian Federation
City	Moscow
Period	24/03/13 → 27/03/13

Keywords

EWI-24058
METIS-300200
IR-88458

Access to Document

10.1007/978-3-642-36973-5_63

ecir2013snippets

Cite this

Demeester, T., Nguyen, D.-P., Trieschnigg, R. B., Develder, C., & Hiemstra, D. (2013). Snippet-based relevance predictions for federated web search. In Advances in Information Retrieval, Proceedings of the 35th European Conference on IR Research, ECIR 2013 (pp. 697-700). (Lecture Notes in Computer Science; Vol. 7814). Springer. https://doi.org/10.1007/978-3-642-36973-5_63

@inproceedings{e97afc7272304250b50ba4c25b580701,

title = "Snippet-based relevance predictions for federated web search",

abstract = "How well can the relevance of a page be predicted, purely based on snippets? This would be highly useful in a Federated Web Search setting where caching large amounts of result snippets is more feasible than caching entire pages. The experiments reported in this paper make use of result snippets and pages from a diverse set of actual Web search engines. A linear classifier is trained to predict the snippet-based user estimate of page relevance, but also, to predict the actual page relevance, again based on snippets alone. The presented results confirm the validity of the proposed approach and provide promising insights into future result merging strategies for a Federated Web Search setting.",

keywords = "EWI-24058, METIS-300200, IR-88458",

author = "Thomas Demeester and Dong-Phuong Nguyen and Trieschnigg, {Rudolf Berend} and Chris Develder and Djoerd Hiemstra",

note = "10.1007/978-3-642-36973-5_63 ; 35th European Conference on Information Retrieval, ECIR 2013 ; Conference date: 24-03-2013 Through 27-03-2013",

year = "2013",

month = mar,

doi = "10.1007/978-3-642-36973-5_63",

language = "Undefined",

isbn = "978-3-642-36972-8",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "697--700",

booktitle = "Advances in Information Retrieval, Proceedings of the 35th European Conference on IR Research, ECIR 2013",

address = "Germany",

}

Demeester, T, Nguyen, D-P, Trieschnigg, RB, Develder, C & Hiemstra, D 2013, Snippet-based relevance predictions for federated web search. in Advances in Information Retrieval, Proceedings of the 35th European Conference on IR Research, ECIR 2013. Lecture Notes in Computer Science, vol. 7814, Springer, Berlin, pp. 697-700, 35th European Conference on Information Retrieval, ECIR 2013, Moscow, Russian Federation, 24/03/13. https://doi.org/10.1007/978-3-642-36973-5_63

Snippet-based relevance predictions for federated web search. / Demeester, Thomas; Nguyen, Dong-Phuong; Trieschnigg, Rudolf Berend et al.
Advances in Information Retrieval, Proceedings of the 35th European Conference on IR Research, ECIR 2013. Berlin: Springer, 2013. p. 697-700 (Lecture Notes in Computer Science; Vol. 7814).

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

TY - GEN

T1 - Snippet-based relevance predictions for federated web search

AU - Demeester, Thomas

AU - Nguyen, Dong-Phuong

AU - Trieschnigg, Rudolf Berend

AU - Develder, Chris

AU - Hiemstra, Djoerd

N1 - Conference code: 35

PY - 2013/3

Y1 - 2013/3

N2 - How well can the relevance of a page be predicted, purely based on snippets? This would be highly useful in a Federated Web Search setting where caching large amounts of result snippets is more feasible than caching entire pages. The experiments reported in this paper make use of result snippets and pages from a diverse set of actual Web search engines. A linear classifier is trained to predict the snippet-based user estimate of page relevance, but also, to predict the actual page relevance, again based on snippets alone. The presented results confirm the validity of the proposed approach and provide promising insights into future result merging strategies for a Federated Web Search setting.

AB - How well can the relevance of a page be predicted, purely based on snippets? This would be highly useful in a Federated Web Search setting where caching large amounts of result snippets is more feasible than caching entire pages. The experiments reported in this paper make use of result snippets and pages from a diverse set of actual Web search engines. A linear classifier is trained to predict the snippet-based user estimate of page relevance, but also, to predict the actual page relevance, again based on snippets alone. The presented results confirm the validity of the proposed approach and provide promising insights into future result merging strategies for a Federated Web Search setting.

KW - EWI-24058

KW - METIS-300200

KW - IR-88458

U2 - 10.1007/978-3-642-36973-5_63

DO - 10.1007/978-3-642-36973-5_63

M3 - Conference contribution

SN - 978-3-642-36972-8

T3 - Lecture Notes in Computer Science

SP - 697

EP - 700

BT - Advances in Information Retrieval, Proceedings of the 35th European Conference on IR Research, ECIR 2013

PB - Springer

CY - Berlin

T2 - 35th European Conference on Information Retrieval, ECIR 2013

Y2 - 24 March 2013 through 27 March 2013

ER -