Language Models for Relevance Feedback Export

@incollection{Book:1998:Ponte, abstract = {The language modeling approach to Information Retrieval (IR) is a conceptually simple model of IR originally developed by Ponte and Croft (1998). In this approach, the query is treated as a random event and documents are ranked according to the likelihood that the query would be generated via a language model estimated for each document. The intuition behind this approach is that users have a prototypical document in mind and will choose query terms accordingly. The intuitive appeal of this method is that inferences about the semantic content of documents do not need to be made resulting in a conceptually simple model. In this paper, techniques for relevance feedback and routing are derived from the language modeling approach in a straightforward manner and their effectiveness is demonstrated empirically. These experiments demonstrate further proof of concept for the language modeling approach to retrieval.}, author = {Ponte, Jay}, citeulike-article-id = {2187445}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/0-306-47019-5_3}, doi = {10.1007/0-306-47019-5_3}, journal = {Advances in Information Retrieval}, keywords = {document\_model, ir, lm, query\_expansion, query\_model, query\_modeling, relevance\_feedback, retrieval\_model, rocchio}, pages = {73--95}, posted-at = {2009-01-14 17:48:35}, priority = {0}, title = {Language Models for Relevance Feedback}, url = {http://dx.doi.org/10.1007/0-306-47019-5_3}, year = {2002} }

TY - CHAP ID - Book:1998:Ponte L3 - citeulike-article-id:2187445 N2 - The language modeling approach to Information Retrieval (IR) is a conceptually simple model of IR originally developed by Ponte and Croft (1998). In this approach, the query is treated as a random event and documents are ranked according to the likelihood that the query would be generated via a language model estimated for each document. The intuition behind this approach is that users have a prototypical document in mind and will choose query terms accordingly. The intuitive appeal of this method is that inferences about the semantic content of documents do not need to be made resulting in a conceptually simple model. In this paper, techniques for relevance feedback and routing are derived from the language modeling approach in a straightforward manner and their effectiveness is demonstrated empirically. These experiments demonstrate further proof of concept for the language modeling approach to retrieval. JF - Advances in Information Retrieval EP - 95 TI - Language Models for Relevance Feedback SP - 73 KW - document_model KW - ir KW - lm KW - query_expansion KW - query_model KW - query_modeling KW - relevance_feedback KW - retrieval_model KW - rocchio AU - Ponte, Jay PY - 2002/// UR - http://dx.doi.org/10.1007/0-306-47019-5_3 ER -