Topic based language models for ad hoc information retrieval

We propose a topic based approach to language modelling for ad-hoc information retrieval (IR). Many smoothed estimators used for the multinomial query model in IR rely upon the estimated background collection probabilities. In this paper, we propose a topic based language modelling approach, that us...

Full description

Saved in:
Bibliographic Details
Published in2004 IEEE International Joint Conference on Neural Networks Vol. 4; pp. 3281 - 3286 vol.4
Main Authors Azzopardi, L., Girolami, M., van Rijsbergen, C.J.
Format Conference Proceeding
LanguageEnglish
Published Piscataway NJ IEEE 2004
Subjects
Applied sciences
Artificial intelligence
Computer science; control theory; systems
Exact sciences and technology
Hidden Markov models
Information retrieval
Information systems. Data bases
Mathematical model
Memory organisation. Data processing
Optical computing
Smoothing methods
Software
Vocabulary
Information retrieval
Modelling language
Neural network
Probabilistic approach
Database query
Modeling
Online AccessGet full text
ISBN0780383591
9780780383593
ISSN1098-7576
DOI10.1109/IJCNN.2004.1381205

Cover

More Information
Summary:We propose a topic based approach to language modelling for ad-hoc information retrieval (IR). Many smoothed estimators used for the multinomial query model in IR rely upon the estimated background collection probabilities. In this paper, we propose a topic based language modelling approach, that uses a more informative prior based on the topical content of a document. In our experiments, the proposed model provides comparable IR performance to the standard models, but when combined in a two stage language model, it outperforms all other estimated models.
ISBN:0780383591
9780780383593
ISSN:1098-7576
DOI:10.1109/IJCNN.2004.1381205