A predictive framework for retrieving the best answer

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

73 Citations (Scopus)

Abstract

In a question answering (QA) system, each user interaction with the system is different and since there are a variety of arguably correct answers to complex questions, identifying factors for improving the quality of the retrieved answer is difficult. This research aims to develop a framework that identifies predictive variables for the best quality answer in a QA system. It was found that accuracy, completeness and relevance were predictors of best answer. We believe that these findings can serve to guide future developments in the answer extraction modules in the QA systems.

Original languageEnglish
Title of host publicationProceedings of the 23rd Annual ACM Symposium on Applied Computing, SAC'08
Pages1107-1111
Number of pages5
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event23rd Annual ACM Symposium on Applied Computing, SAC'08 - Fortaleza, Ceara, Brazil
Duration: Mar 16 2008Mar 20 2008

Publication series

NameProceedings of the ACM Symposium on Applied Computing

Conference

Conference23rd Annual ACM Symposium on Applied Computing, SAC'08
Country/TerritoryBrazil
CityFortaleza, Ceara
Period3/16/083/20/08

ASJC Scopus Subject Areas

  • Software

Keywords

  • Answer quality
  • Prediction model

Fingerprint

Dive into the research topics of 'A predictive framework for retrieving the best answer'. Together they form a unique fingerprint.

Cite this