The feasibility of machine learning for query answering-an experiment in two domains

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

Abstract

We present an experiment in which an information retrieval system using a forest of decision trees was trained using Utgoff's ITI algorithm on two test collections. The system was then compared with a conventional inverted indexing engine and found to give a superior performance. We argue that the method has the potential to be used in real applications where the task domain is homogeneous.

Original languageEnglish
Title of host publicationArtificial Intelligence and Cognitive Science - 13th Irish Conference, AICS 2002, Proceedings
EditorsMichael O’Neill, Richard F. E. Sutcliffe, Conor Ryan, Malachy Eaton, Niall J. L. Griffith
PublisherSpringer Verlag
Pages119-126
Number of pages8
ISBN (Electronic)3540441840, 9783540441847
DOIs
Publication statusPublished - 2002
Event13th Irish Conference on Artificial Intelligence and Cognitive Science, AICS 2002 - Limerick, Ireland
Duration: 12 Sep 200213 Sep 2002

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume2464
ISSN (Print)0302-9743

Conference

Conference13th Irish Conference on Artificial Intelligence and Cognitive Science, AICS 2002
Country/TerritoryIreland
CityLimerick
Period12/09/0213/09/02

Fingerprint

Dive into the research topics of 'The feasibility of machine learning for query answering-an experiment in two domains'. Together they form a unique fingerprint.

Cite this