Skip to main navigation Skip to search Skip to main content

An extended query performance prediction framework utilizing passage-level information

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

We show that document-level post-retrieval query performance prediction (QPP) methods are mostly suited for short query prediction tasks; such methods perform significantly worse in verbose (long and informative) query prediction settings. To address the prediction quality gap among query lengths, we propose a novel passage-level post-retrieval QPP framework. Our empirical analysis demonstrates that, those QPP methods that utilize passage-level information are much better suited for verbose QPP settings. Moreover, our proposed predictors, which utilize both document-level and passage-level information provide a more robust prediction which is less sensitive to query length.

Original languageEnglish
Title of host publicationICTIR 2018 - Proceedings of the 2018 ACM SIGIR International Conference on the Theory of Information Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages35-42
Number of pages8
ISBN (Electronic)9781450356565
DOIs
StatePublished - 10 Sep 2018
Externally publishedYes
Event8th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2018 - Tianjin, China
Duration: 14 Sep 201817 Sep 2018

Publication series

NameICTIR 2018 - Proceedings of the 2018 ACM SIGIR International Conference on the Theory of Information Retrieval

Conference

Conference8th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2018
Country/TerritoryChina
CityTianjin
Period14/09/1817/09/18

ASJC Scopus subject areas

  • Information Systems
  • Computer Science (miscellaneous)

Fingerprint

Dive into the research topics of 'An extended query performance prediction framework utilizing passage-level information'. Together they form a unique fingerprint.

Cite this