Retrieval through explanation: an abductive inference approach to relevance feedback

I. Ruthven, M. Lalmas, C.J. van Rijsbergen, D.G. Bridge (Editor), R.M. Byrne (Editor), B. O'Sullivan (Editor), S. Prestwich (Editor), H. Sorensen (Editor)

Research output: Contribution to conferencePaper

Abstract

Relevance feedback techniques are designed to automatically improve a system's representation of a query by using documents the user has marked as relevant. However, traditional relevance feedback models suffer from a number of limitations that restrict their potential in supporting information seeking. One of the major limitations of relevance feedback is that it does not incorporate behavioural aspects of information seeking - how and why users assess relevance. We propose that relevance feedback should be viewed as a process of explanation and demonstrate how this limitation of relevance feedback techniques can be overcome by a theory of relevance feedback based on abductive inference.

Conference

Conference10th Irish Conference on Artificial Intelligence and Cognitive Science
CityCork, Ireland
Period1/09/993/09/99

Fingerprint

Feedback

Keywords

  • information retrieval
  • abductive inference
  • relevance feedback

Cite this

Ruthven, I., Lalmas, M., van Rijsbergen, C. J., Bridge, D. G. (Ed.), Byrne, R. M. (Ed.), O'Sullivan, B. (Ed.), ... Sorensen, H. (Ed.) (1999). Retrieval through explanation: an abductive inference approach to relevance feedback. Paper presented at 10th Irish Conference on Artificial Intelligence and Cognitive Science, Cork, Ireland, .
Ruthven, I. ; Lalmas, M. ; van Rijsbergen, C.J. ; Bridge, D.G. (Editor) ; Byrne, R.M. (Editor) ; O'Sullivan, B. (Editor) ; Prestwich, S. (Editor) ; Sorensen, H. (Editor). / Retrieval through explanation : an abductive inference approach to relevance feedback. Paper presented at 10th Irish Conference on Artificial Intelligence and Cognitive Science, Cork, Ireland, .7 p.
@conference{a77d1bd6e43345079f61a5b1fd4ff929,
title = "Retrieval through explanation: an abductive inference approach to relevance feedback",
abstract = "Relevance feedback techniques are designed to automatically improve a system's representation of a query by using documents the user has marked as relevant. However, traditional relevance feedback models suffer from a number of limitations that restrict their potential in supporting information seeking. One of the major limitations of relevance feedback is that it does not incorporate behavioural aspects of information seeking - how and why users assess relevance. We propose that relevance feedback should be viewed as a process of explanation and demonstrate how this limitation of relevance feedback techniques can be overcome by a theory of relevance feedback based on abductive inference.",
keywords = "information retrieval, abductive inference, relevance feedback",
author = "I. Ruthven and M. Lalmas and {van Rijsbergen}, C.J. and D.G. Bridge and R.M. Byrne and B. O'Sullivan and S. Prestwich and H. Sorensen",
year = "1999",
month = "9",
day = "3",
language = "English",
note = "10th Irish Conference on Artificial Intelligence and Cognitive Science ; Conference date: 01-09-1999 Through 03-09-1999",

}

Ruthven, I, Lalmas, M, van Rijsbergen, CJ, Bridge, DG (ed.), Byrne, RM (ed.), O'Sullivan, B (ed.), Prestwich, S (ed.) & Sorensen, H (ed.) 1999, 'Retrieval through explanation: an abductive inference approach to relevance feedback' Paper presented at 10th Irish Conference on Artificial Intelligence and Cognitive Science, Cork, Ireland, 1/09/99 - 3/09/99, .

Retrieval through explanation : an abductive inference approach to relevance feedback. / Ruthven, I.; Lalmas, M.; van Rijsbergen, C.J.; Bridge, D.G. (Editor); Byrne, R.M. (Editor); O'Sullivan, B. (Editor); Prestwich, S. (Editor); Sorensen, H. (Editor).

1999. Paper presented at 10th Irish Conference on Artificial Intelligence and Cognitive Science, Cork, Ireland, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Retrieval through explanation

T2 - an abductive inference approach to relevance feedback

AU - Ruthven, I.

AU - Lalmas, M.

AU - van Rijsbergen, C.J.

A2 - Bridge, D.G.

A2 - Byrne, R.M.

A2 - O'Sullivan, B.

A2 - Prestwich, S.

A2 - Sorensen, H.

PY - 1999/9/3

Y1 - 1999/9/3

N2 - Relevance feedback techniques are designed to automatically improve a system's representation of a query by using documents the user has marked as relevant. However, traditional relevance feedback models suffer from a number of limitations that restrict their potential in supporting information seeking. One of the major limitations of relevance feedback is that it does not incorporate behavioural aspects of information seeking - how and why users assess relevance. We propose that relevance feedback should be viewed as a process of explanation and demonstrate how this limitation of relevance feedback techniques can be overcome by a theory of relevance feedback based on abductive inference.

AB - Relevance feedback techniques are designed to automatically improve a system's representation of a query by using documents the user has marked as relevant. However, traditional relevance feedback models suffer from a number of limitations that restrict their potential in supporting information seeking. One of the major limitations of relevance feedback is that it does not incorporate behavioural aspects of information seeking - how and why users assess relevance. We propose that relevance feedback should be viewed as a process of explanation and demonstrate how this limitation of relevance feedback techniques can be overcome by a theory of relevance feedback based on abductive inference.

KW - information retrieval

KW - abductive inference

KW - relevance feedback

UR - http://www.cis.strath.ac.uk/research/publications/papers/strath_cis_publication_151.pdf

M3 - Paper

ER -

Ruthven I, Lalmas M, van Rijsbergen CJ, Bridge DG, (ed.), Byrne RM, (ed.), O'Sullivan B, (ed.) et al. Retrieval through explanation: an abductive inference approach to relevance feedback. 1999. Paper presented at 10th Irish Conference on Artificial Intelligence and Cognitive Science, Cork, Ireland, .