Output details
11 - Computer Science and Informatics
University of Greenwich
Return to search
Output 0 of 0 in the submission
Output title
Learning in a pairwise term-term proximity framework for information retrieval
Type
E - Conference contribution
Name of conference/published proceedings
SIGIR '09. Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Volume number
-
Issue number
-
First page of article
251
ISSN of proceedings
-
Year of publication
2009
Number of additional authors
1
Additional information
H.3.3 The proximity of query terms (i.e. words) in text are a useful clue in determining if the piece of text is relevant to a given query. This paper outlines a comprehensive set of features that may be useful in developing new approaches for ranking relevant documents in terms of relevance. This is particularly useful for web search and other information retrieval applications. The paper develops a novel framework for incorporating these proximity features into ranking functions. It has been well-cited (30 citations at the time of writing this description) since publication.
Interdisciplinary
-
Cross-referral requested
-
Research group
3 - Computer & Computational Science
Citation count
19
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
