As stable as you are: Re-ranking search results using query-drift analysis

Haggai Roitman; Ella Rabinovich; Oren Sar Shalom

doi:10.1145/3209542.3209567

As stable as you are: Re-ranking search results using query-drift analysis

Haggai Roitman
, Ella Rabinovich
, Oren Sar Shalom

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

Abstract

This work studies the merits of using query-drift analysis for search re-ranking. A relationship between the ability to predict the quality of a result list retrieved by an arbitrary method, as manifested by its estimated query-drift, and the ability to improve that method's initial retrieval by re-ranking documents in the list based on such prediction is established. A novel document property, termed "aspectstability", is identified as the main enabler for transforming the output of an aspect-level query-drift analysis into concrete document scores for search re-ranking. Using an evaluation with various TREC corpora with common baseline retrieval methods, the potential of the proposed re-ranking approach is demonstrated.

Original language	English
Title of host publication	HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media
Publisher	Association for Computing Machinery, Inc
Pages	33-37
Number of pages	5
ISBN (Electronic)	9781450354271
DOIs	https://doi.org/10.1145/3209542.3209567
State	Published - 3 Jul 2018
Externally published	Yes
Event	29th ACM International Conference on Hypertext and Social Media, HT 2018 - Baltimore, United States Duration: 9 Jul 2018 → 12 Jul 2018

Publication series

Name	HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media

Conference

Conference	29th ACM International Conference on Hypertext and Social Media, HT 2018
Country/Territory	United States
City	Baltimore
Period	9/07/18 → 12/07/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computing Machinery.

ASJC Scopus subject areas

Software
Artificial Intelligence
Human-Computer Interaction
Computer Graphics and Computer-Aided Design

Access to Document

10.1145/3209542.3209567

Cite this

Roitman, H., Rabinovich, E., & Shalom, O. S. (2018). As stable as you are: Re-ranking search results using query-drift analysis. In HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media (pp. 33-37). (HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media). Association for Computing Machinery, Inc. https://doi.org/10.1145/3209542.3209567

@inproceedings{4a6f8c7c90d24a3fb77957b373d50ab7,

title = "As stable as you are: Re-ranking search results using query-drift analysis",

abstract = "This work studies the merits of using query-drift analysis for search re-ranking. A relationship between the ability to predict the quality of a result list retrieved by an arbitrary method, as manifested by its estimated query-drift, and the ability to improve that method's initial retrieval by re-ranking documents in the list based on such prediction is established. A novel document property, termed {"}aspectstability{"}, is identified as the main enabler for transforming the output of an aspect-level query-drift analysis into concrete document scores for search re-ranking. Using an evaluation with various TREC corpora with common baseline retrieval methods, the potential of the proposed re-ranking approach is demonstrated.",

author = "Haggai Roitman and Ella Rabinovich and Shalom, \{Oren Sar\}",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 29th ACM International Conference on Hypertext and Social Media, HT 2018 ; Conference date: 09-07-2018 Through 12-07-2018",

year = "2018",

month = jul,

day = "3",

doi = "10.1145/3209542.3209567",

language = "English",

series = "HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media",

publisher = "Association for Computing Machinery, Inc",

pages = "33--37",

booktitle = "HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media",

}

Roitman, H, Rabinovich, E & Shalom, OS 2018, As stable as you are: Re-ranking search results using query-drift analysis. in HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media. HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media, Association for Computing Machinery, Inc, pp. 33-37, 29th ACM International Conference on Hypertext and Social Media, HT 2018, Baltimore, United States, 9/07/18. https://doi.org/10.1145/3209542.3209567

As stable as you are: Re-ranking search results using query-drift analysis. / Roitman, Haggai; Rabinovich, Ella; Shalom, Oren Sar.
HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2018. p. 33-37 (HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media).

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

TY - GEN

T1 - As stable as you are

T2 - 29th ACM International Conference on Hypertext and Social Media, HT 2018

AU - Roitman, Haggai

AU - Rabinovich, Ella

AU - Shalom, Oren Sar

PY - 2018/7/3

Y1 - 2018/7/3

N2 - This work studies the merits of using query-drift analysis for search re-ranking. A relationship between the ability to predict the quality of a result list retrieved by an arbitrary method, as manifested by its estimated query-drift, and the ability to improve that method's initial retrieval by re-ranking documents in the list based on such prediction is established. A novel document property, termed "aspectstability", is identified as the main enabler for transforming the output of an aspect-level query-drift analysis into concrete document scores for search re-ranking. Using an evaluation with various TREC corpora with common baseline retrieval methods, the potential of the proposed re-ranking approach is demonstrated.

AB - This work studies the merits of using query-drift analysis for search re-ranking. A relationship between the ability to predict the quality of a result list retrieved by an arbitrary method, as manifested by its estimated query-drift, and the ability to improve that method's initial retrieval by re-ranking documents in the list based on such prediction is established. A novel document property, termed "aspectstability", is identified as the main enabler for transforming the output of an aspect-level query-drift analysis into concrete document scores for search re-ranking. Using an evaluation with various TREC corpora with common baseline retrieval methods, the potential of the proposed re-ranking approach is demonstrated.

UR - https://www.scopus.com/pages/publications/85051473019

U2 - 10.1145/3209542.3209567

DO - 10.1145/3209542.3209567

M3 - Conference contribution

AN - SCOPUS:85051473019

T3 - HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media

SP - 33

EP - 37

BT - HT 2018 - Proceedings of the 29th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery, Inc

Y2 - 9 July 2018 through 12 July 2018

ER -

As stable as you are: Re-ranking search results using query-drift analysis

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this