81 Hits in 5.9 sec

Natural language information retrieval

Tomek Strzalkowski
1996 Proceedings of a workshop on held at Vienna, Virginia May 6-8, 1996 -  
The evaluation results discussed here were obtained in connection with the 3rd and 4th Text Retrieval Conferences (TREC-3 and TREC-4).  ...  We report on the joint GE/NYU natural language information retrieval project as related to the Tipster Phase 2 research conducted initially at NYU and subsequently at GE R&D Center and NYU.  ...  Will Rogers provided valuable assistance in installing updated versions of PRISE at NYU.  ... 
doi:10.3115/1119018.1119052 dblp:conf/tipster/Strzalkowski96 fatcat:5iter7rrffe27jolftaxcmtm7m

Finding relevant passages using noun-noun compounds (poster session)

Eduard Hoenkamp, Rob de Groot
2000 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '00  
Yet, evidence that phrases would be more effective for information retrieval is inconclusive.  ...  In an experiment, a variety of meaningful NNCs were used to isolate relevant passages in a large and varied corpus.  ...  For each query in this set, a boolean proximity matching iso- For coherence matching to occur, a passage must contain one of the following; TREC-3: Experience with conceptual relations in information  ... 
doi:10.1145/345508.345667 dblp:conf/sigir/HoenkamG00 fatcat:5tdbaqbiyffntmtuzr53w56r4m

Natural language information retrieval in digital libraries

Tomek Strzalkowski, Jose Perez-Carballo, Mihnea Marinescu
1996 Proceedings of the first ACM international conference on Digital libraries - DL '96  
In this paper we report on some recent developments in joint NYU and GE natural language information retrieval system.  ...  This system has been used in NIST-sponscx-ed Text Retrieval Conferences (TREC), where we worked with approximately 3.3 GB ytes of text articles including material from the Wall Street Journal, the Associated  ...  Will Rogers provided vahtable assistance in installing updated versions of PRISE at NYU.  ... 
doi:10.1145/226931.226954 dblp:conf/dl/StrzalkowskiCM96 fatcat:ynrz5nablradpn5cdh5bpa4rde

Natural language information retrieval

Tomek Strzalkowski
1995 Information Processing & Management  
I ABSTRACT n this paper we report on the joint GE/NYU natural 4 language information retrieval project as related to the th Text Retrieval Conference (TREC-4).  ...  Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently  ...  A notble exception is the new massive query expansion a p module used in routing experiments, which replaces rototype extension used in the TREC-3 system.  ... 
doi:10.1016/0306-4573(94)00055-8 fatcat:zzqn7zkuivhdtoa57lq5ulv3oe

Term necessity prediction

Le Zhao, Jamie Callan
2010 Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10  
in retrieval accuracy.  ...  Experiments with two popular retrieval models and 6 standard datasets demonstrate that using predicted term necessity estimates as user term weights of the original query terms leads to significant improvements  ...  Smaller datasets with more complete judgments include ad-hoc retrieval tracks of TREC 3 to 8.  ... 
doi:10.1145/1871437.1871474 dblp:conf/cikm/ZhaoC10 fatcat:h335fq5ecfbcvpo5yu7ln2qwia

Evaluating exploratory search systems

Ryen W. White, Gary Marchionini, Gheorghe Muresan
2008 Information Processing & Management  
Since TREC-3, the conference has extended its mandate to recognize the importance of the user in information-seeking.  ...  Since the days of the Cranfield experiments some 40 years ago, the issue of evaluating retrieval systems has been considered highly important by the Information Retrieval (IR) community [2] .  ...  Since TREC-3, the conference has extended its mandate to recognize the importance of the user in information-seeking.  ... 
doi:10.1016/j.ipm.2007.09.011 fatcat:75ymstsmvfgbvjjnrnhnvw5wza

Page 64 of Library & Information Science Abstracts Vol. , Issue 9 [page]

1995 Library & Information Science Abstracts  
Reports text information retrieval experiments performed as part of the 3rd round of Text Retrieval Conferences (TREC) using the Okapi online catalogue system at City University, UK.  ...  Explores the retrieval and user issues related to the impact of including table of contents notes as a searchable field in online catalogues.  ... 

Automatic feedback using past queries

Larry Fitzpatrick, Mei Dent
1997 Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '97  
Automatic past-query feedback actually improved top document precision in this experiment.  ...  Automatic feedback of documents identified from similar past queries was compared with standard top-document feedback and with no feedback.  ...  The weight for each position was empirically derived from the relevance ranked result lists of 50 TREC-3 ad hoc queries against the TREC-3 data collection.  ... 
doi:10.1145/258525.258597 dblp:conf/sigir/FitzpatrickD97 fatcat:kanrng7uxvappejiyze2zrfacu

Modeling and solving term mismatch for full-text retrieval

Le Zhao
2012 SIGIR Forum  
The term mismatch problem is a long standing problem in information retrieval.  ...  Jamie has given me the opportunity to work on a large number of tasks related to my interest in core retrieval modeling.  ...  Test term coverage seems to correlate with retrieval performance. With more test term coverage (training on TREC 3-5 or TREC 3-7) retrieval performance is much closer to the 2-pass method.  ... 
doi:10.1145/2422256.2422277 fatcat:iboh56u5kvdrhcnt4uqyorwvp4

Data fusion according to the principle of polyrepresentation

Birger Larsen, Peter Ingwersen, Berit Lund
2009 Journal of the American Society for Information Science and Technology  
Data fusion improves retrieval performance over their constituent IR models only if the models all are quite conceptually/algorithmically dissimilar and equally and well performing, in that order of importance  ...  This principle is based on cognitive IR perspective (Ingwersen & Järvelin, 2005) and implies that each retrieval model is regarded as a representation of a unique interpretation of information retrieval  ...  Acknowledgment The authors thank Jaana Kekäläinen as well as one reviewer for their valuable comments, and the Nordic Research School in Library and Information Science (NORSLIS) for its travel and mobility  ... 
doi:10.1002/asi.21028 fatcat:i4lmn24igncjvfl2wmnduur4vq

The impact of text browsing on text retrieval performance

Richard C. Bodner, Mark H. Chignell, Nipon Charoenkitkarn, Gene Golovchinsky, Richard W. Kopak
2001 Information Processing & Management  
A major outcome from our experiments at TREC and with the TREC data, is that hypertext interfaces to information retrieval (IR) tasks tend to increase recall.  ...  In an experiment where a traditional (type-in) query interface was contrasted with a condition where queries were marked up on the text, the improvement in recall due to viewing more text was more pronounced  ...  (ITRC) to the second author and by the Communications and Information Technology of Ontario (CITO).  ... 
doi:10.1016/s0306-4573(00)00059-5 fatcat:ubyihqmotjgklm7pwzccv77oky

"A term is known by the company it keeps": On Selecting a Good Expansion Set in Pseudo-Relevance Feedback [chapter]

Raghavendra Udupa, Abhijit Bhole, Pushpak Bhattacharyya
2009 Lecture Notes in Computer Science  
It is well known that pseudo-relevance feedback (PRF) improves the retrieval performance of Information Retrieval (IR) systems in general.  ...  We demonstrate on several test collections that expansion terms can be partitioned into two sets and the best of the two sets gives substantial improvements in retrieval performance over model-based feedback  ...  Introduction Pseudo-relevance feedback (PRF) is a well-known method for query expansion in Information Retrieval (IR) [1] .  ... 
doi:10.1007/978-3-642-04417-5_10 fatcat:t35ywhda5ffflooca3nig2aoqm

Phase-based information retrieval

A.T. Arampatzis, T. Tsoris, C.H.A. Koster, Th.P. van der Weide
1998 Information Processing & Management  
In this respect, we introduce the phrase retrieval hypothesis to replace the keyword retrieval hypothesis.  ...  Guided by the failures and successes of other state-of-the-art approaches, as well as our own experience with the IRENA system, our approach is based on phrases and incorporates linguistic resources and  ...  shown before by a number of groups in TREC-3 and elsewhere).  ... 
doi:10.1016/s0306-4573(98)00030-2 fatcat:xvp3dr56enh2hdz7lsa6lj6ti4

The TREC interactive track: an annotated bibliography

Paul Over
2001 Information Processing & Management  
The main arena for such work has been the Interactive Track (TREC 3±8).  ...  The study of interactive information retrieval (IR) has been a small but constant part of the Text REtrieval Conferences (TREC 1±8) from the beginning.  ...  query mode (TREC 1, 2). · Manual query mode (TREC 1±8). · Interactive Track (TREC 3±8). · High Precision Track (TREC 6, 7).  ... 
doi:10.1016/s0306-4573(00)00053-4 fatcat:zq2tlzcdx5fi3fqnruwxr2nehe

Recommended reading for IR research students

Alistair Moffat, Justin Zobel, David Hawking
2005 SIGIR Forum  
The IR community is fortunate in already having an excellent compendium of past research, the edited volume Readings in Information Retrieval (K. Sparck Jones and P.  ...  The distribution of nominated papers by year is roughly skewed normal, with a median of 1998. The skew is in favor of recent papers.  ...  Gatford, TREC-3, 1994) Commentary: This paper (and associated TREC-3 runs) introduced the BM25 weighting formula and demonstrated that it worked very well.  ... 
doi:10.1145/1113343.1113344 fatcat:lx4laud5urhh7ediq3z2vi66ju
« Previous Showing results 1 — 15 out of 81 results