Filters








22,608 Hits in 3.8 sec

Efficient passage ranking for document databases

Marcin Kaszkiel, Justin Zobel, Ron Sacks-Davis
1999 ACM Transactions on Information Systems  
An alternative retrieval method is to rank passages, that is, short fragments of documents, a strategy that can improve effectiveness and identify relevant material in documents that are too large for  ...  Compared to passage ranking with adaptations of current document ranking algorithms, our new "DO-TOS" passage-ranking algorithm requires only a fraction of the resources, at the cost of a small loss of  ...  ACKNOWLEDGMENTS We are grateful to the anonymous referees for their extensive comments and feedback.  ... 
doi:10.1145/326440.326445 fatcat:ixas4xlmzzb3rmnysfwx35m7ty

Approximating the top-m passages in a parallel question answering system

Charles L. A. Clarke, Egidio L. Terra
2004 Proceedings of the Thirteenth ACM conference on Information and knowledge management - CIKM '04  
The paper is structured around a specific application -passage retrieval for question answering -but the primary results are more broadly applicable.  ...  We examine the problem of retrieving the top-m ranked items from a large collection, randomly distributed across an n-node system.  ...  It would be eliminated from the final ranked list of passages, since it either occurs in a document with a higher ranking passage (the nested passage) or overlaps a document boundary.  ... 
doi:10.1145/1031171.1031259 dblp:conf/cikm/ClarkeT04 fatcat:xyd5utwfbzgtzlqvnc54xl5hxy

Effective ranking with arbitrary passages

Marcin Kaszkiel, Justin Zobel
2001 Journal of the American Society for Information Science and Technology  
We show that ranking with these arbitrary passages gives substantial improvements in retrieval effectiveness over traditional document ranking schemes, particularly for queries on collections of long documents  ...  Ranking with arbitrary passages shows consistent improvements compared to ranking with whole documents, and to ranking with previous passage types that depend on document structure or topic shifts in documents  ...  For example, for short queries and text databases of long documents, passages using structural properties of documents are best, whereas, for text databases of uniform document length, only passages that  ... 
doi:10.1002/1532-2890(2000)9999:9999<::aid-asi1075>3.3.co;2-r fatcat:khqoiydhhvabndyhxm6t7odqbi

Parallel computing for passage retrieval

A. MacFarlane, S.E. Robertson, J.A. McCann
2004 ASLIB Proceedings  
In this paper we examine methods for both speeding up passage processing and examining more passages using parallel computers.  ...  We vary the number of passages processed in order to examine the effect on retrieval effectiveness and efficiency.  ...  We are particularly grateful to David Hawking for making the arrangements for the visit to the ANU.  ... 
doi:10.1108/00012530410549231 fatcat:whwsqime3nfqngv7cwxip2xlne

Combining Semantics, Context, and Statistical Evidence in Genomics Literature Search

Jay Urbain, Nazli Goharian, Ophir Frieder
2007 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering  
When ranking documents based on the most relevant extracted passages, the results exceed the state-of-the-art by 13.89% as assessed by the TREC 2005 Genomics track collection of 4.5 million MEDLINE citations  ...  level information versus using document, sentence or passage level information alone.  ...  For passages with the same number of concepts, the passages are further ranked by a query term density match (QTM) measurement we devised and used successfully for the 2006 TREC Genomics track [10] .  ... 
doi:10.1109/bibe.2007.4375738 dblp:conf/bibe/UrbainGF07 fatcat:axaenauynfcwxb5fkd45ljgc4q

Effective ranking with arbitrary passages

Marcin Kaszkiel, Justin Zobel
2001 Journal of the American Society for Information Science and Technology  
We show that ranking with these arbitrary passages gives substantial improvements in retrieval effectiveness over traditional document ranking schemes, particularly for queries on collections of long documents  ...  Ranking with arbitrary passages shows consistent improvements compared to ranking with whole documents, and to ranking with previous passage types that depend on document structure or topic shifts in documents  ...  For example, for short queries and text databases of long documents, passages using structural properties of documents are best, whereas, for text databases of uniform document length, only passages that  ... 
doi:10.1002/1532-2890(2000)9999:9999<::aid-asi1075>3.0.co;2-# fatcat:o6qu5isg5fbyfhosefngb7uwxy

Passage retrieval revisited

Marcin Kaszkiel, Justin Zobel
1997 SIGIR Forum  
Ranking based on passages addresses some of the shortcomings of whole-document ranking.  ...  Our experiments also show that, compared to whole-document ranking, ranking via fixed-length arbitrary psssagea significantly improves retrieval effedivenees, by 870 for TREC disks 2 and 4 and by 18%-37%  ...  Acknowledgements We thank Finn Sacks-Davis for suggesting the query evaluation method for fixed-length passages. We also thank Alistair Moffat and Roes Wdkinaon.  ... 
doi:10.1145/278459.258561 fatcat:kyaslojlhrevvjz4ipvak276oy

Passage retrieval revisited

Marcin Kaszkiel, Justin Zobel
1997 Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '97  
Ranking based on passages addresses some of the shortcomings of whole-document ranking.  ...  Our experiments also show that, compared to whole-document ranking, ranking via fixed-length arbitrary psssagea significantly improves retrieval effedivenees, by 870 for TREC disks 2 and 4 and by 18%-37%  ...  Acknowledgements We thank Finn Sacks-Davis for suggesting the query evaluation method for fixed-length passages. We also thank Alistair Moffat and Roes Wdkinaon.  ... 
doi:10.1145/258525.258561 dblp:conf/sigir/KaszkielZ97 fatcat:dprarqhxabfsxidvqpvpyb7xze

Shortest-substring retrieval and ranking

Charles L. A. Clarke, Gordon V. Cormack
2000 ACM Transactions on Information Systems  
We present a model for arbitrary passage retrieval using Boolean queries.  ...  Since ranking is based on arbitrary passages, the structural elements to be ranked may be specified at query time and do not need to be restricted to predefined elements. reasonably easy for a user to  ...  The interface used for creating the queries took advantage of the passage retrieval capabilities of shortest-substring ranking for query refinement.  ... 
doi:10.1145/333135.333137 fatcat:lxsz5tnppjevnj3q76ryuz5oji

An expert system for automatic query reformation

Susan Gauch, John B. Smith
1993 Journal of the American Society for Information Science  
Blair and Maron (1985) paint an even bleaker picture for searching full-text databases.  ...  There was no significant difference in the recall achieved by the three system configurations. 3) Overall, the expert system ranked relevant passages above irrelevant passages.  ...  Ranking algorithms for document retrieval systems have been extensively studied (Harman, 1986 ). There has been less work done on ranking for passage retrieval systems.  ... 
doi:10.1002/(sici)1097-4571(199304)44:3<124::aid-asi2>3.0.co;2-c fatcat:rutler5tubh6ddn44ax32hrvr4

INSIDE SOURCEFINDER: PREDICTING THE ACCEPTABILITY STATUS OF CANDIDATE READING-COMPREHENSION SOURCE DOCUMENTS

Kathleen M. Sheehan, Irene Kostin, Yoko Futagi, Ramin Hemat, Daniel Zuckerman
2006 ETS Research Report Series  
The system uses a combination of classification and regression techniques to predict the probability that a given document will be deemed acceptable for use in completing a specified passage-creation assignment  ...  This paper describes the development, implementation, and evaluation of an automated system for predicting the acceptability status of candidate reading-comprehension stimuli extracted from a database  ...  Retrieved documents were stored in a database for later consideration.  ... 
doi:10.1002/j.2333-8504.2006.tb02030.x fatcat:vigznjtoknek5pomtb3teh6w2m

Search improvement via automatic query reformulation

Susan Gauch, John B. Smith
1991 ACM Transactions on Information Systems  
There was no significant difference in the recall achieved by the three system configurations. 3) Overall, the expert system ranked relevant passages above irrelevant passages.  ...  To address these problems, an expert system for online search assistance was developed.  ...  The user's initial query is used to rank-order the documents in the database. The top-ranked documents are presented to the user who indicates which are relevant.  ... 
doi:10.1145/125187.125193 fatcat:ft7zm3z565dx5j2crm2rwnk3x4

An expert system for searching in full-text

Susan Gauch, John B. Smith
1989 Information Processing & Management  
We are developing an intelligent search intermediary to help end-users locate relevant passages in large full-text databases.  ...  & 5 ' This project applies expert system technology to the task of searching online full-text documents.  ...  For a commercial database of many texts or documents the thesaurus would need to be broader in scope.  ... 
doi:10.1016/0306-4573(89)90043-5 fatcat:l2vfwnsilbg6jkmyokokohps3e

Evaluation of an expert system for searching in full text

S. Gauch
1990 Proceedings of the 13th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '90  
In addition, the expert system ranks the retrieved passages in decreasing order of probable relevance.  ...  There was no significant difference in the recall achieved by the three system configurations. 3) Overall, the expert system ranked relevant passages above irrelevant passages.  ...  Hypothesis 2: The expert system improves the search efficiency for a novice searcher. Hypothesis 3: The expert system can rank the passages retrieved by the search in decreasing order of relevance.  ... 
doi:10.1145/96749.98231 dblp:conf/sigir/Gauch90 fatcat:wefrbfxwhfdylb5ycq4dbkr4u4

Term-ordered query evaluation versus document-ordered query evaluation for large document databases

Marcin Kaszkiel, Justin Zobel
1998 Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '98  
There are two main families of technique for eficient processing of ranked queries on large text collections: document-ordered processing and term-ordered processing.  ...  We show that they have similar costs for short queries, but that for long queries document-ordered processing is much more costly.  ...  Number of terms Overall, we conclude that TO' processing using limited accumulators and skipping is effective and efficient, and is the preferred query evaluation mechanism for large document databases  ... 
doi:10.1145/290941.291031 dblp:conf/sigir/KaszkielZ98 fatcat:qwsbnmhtojezbdd32wiwjvbs7q
« Previous Showing results 1 — 15 out of 22,608 results