A Generative Theory of Relevance
Abstract
We present a new theory of relevance for the field of Information Retrieval. Relevance is viewed as a generative process and we hypothesize that both user queries and relevant documents represent random observations from that process. Based on this view we develop a formal retrieval model that has direct applications to a wide range of search scenarios. The new model substantially outperforms strong baselines on the tasks of ad-hoc retrieval, cross-language retrieval, handwriting retrieval, automatic image annotation, video retrieval and topic detection and tracking. Empirical success of our approach is due to a new technique we propose for modeling exchangeable sequences of discrete random variable. The new technique represents an attractive counterpart to existing formulations, such as multinomial mixtures, pLSI and LDA:it is effective, easy to train, and makes no assumptions about the geometric structure of the data.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2004
- Accession Number
- ADA440135
Entities
People
- Victor Lavrenko
Organizations
- University of Massachusetts Amherst