Skip to content

Proceedings - Interactive 2002

TREC 2002 Interactive Track Report

William R. Hersh

Abstract

For TREC 2002, the Interactive Track completed the two-year cycle of observational studies begun in TREC 2001 and followed now by more controlled laboratory experiments focusing on question answering using Web data. Six research groups participated this year.

Bibtex 
@inproceedings{DBLP:conf/trec/Hersh02,
    author = {William R. Hersh},
    editor = {Ellen M. Voorhees and Lori P. Buckland},
    title = {{TREC} 2002 Interactive Track Report},
    booktitle = {Proceedings of The Eleventh Text REtrieval Conference, {TREC} 2002, Gaithersburg, Maryland, USA, November 19-22, 2002},
    series = {{NIST} Special Publication},
    volume = {500-251},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {2002},
    url = {http://trec.nist.gov/pubs/trec11/papers/INTERACTIVE.OHSU.pdf},
    timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
    biburl = {https://dblp.org/rec/conf/trec/Hersh02.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

University of Glasgow at the Web Track of TREC 2002

Vassilis Plachouras, Iadh Ounis, Gianni Amati, C. J. van Rijsbergen

Abstract

The aim of our participation in the topic distillation and the named page finding tasks of the Web track is the evaluation of a well-founded modular probabilistic framework for Web Information Retrieval, which integrates content and link analyses. The link analysis component of the framework employs a new probabilistic approach, called the Absorbing Model, for calculating a measure of popularity for documents induced from the Web graph. [...]

Bibtex 
@inproceedings{DBLP:conf/trec/PlachourasOAR02,
    author = {Vassilis Plachouras and Iadh Ounis and Gianni Amati and C. J. van Rijsbergen},
    editor = {Ellen M. Voorhees and Lori P. Buckland},
    title = {University of Glasgow at the Web Track of {TREC} 2002},
    booktitle = {Proceedings of The Eleventh Text REtrieval Conference, {TREC} 2002, Gaithersburg, Maryland, USA, November 19-22, 2002},
    series = {{NIST} Special Publication},
    volume = {500-251},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {2002},
    url = {http://trec.nist.gov/pubs/trec11/papers/glasgow.web.pdf},
    timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
    biburl = {https://dblp.org/rec/conf/trec/PlachourasOAR02.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

More Statistical Power Needed: The OHSU TREC 2002 Interactive Track Experiments

William R. Hersh, Susan Moy, Dale Kraemer, Lynetta Sacherek, Daniel Olson

Abstract

The original goal for the Oregon Health & Science University (OHSU) TREC 2002 Interactive Track experiments was to perform some preliminary experiments comparing searching on tablet devices versus ordinary personal computers. Unfortunately, the vendor who had promised the devices we planned to use was unable to deliver them in time for the experiments. We therefore shifted our experimental focus to assessing user factors found in previous experiments to be associated with success, with a particular desire to assess the role of spatial visualization. [...]

Bibtex 
@inproceedings{DBLP:conf/trec/HershMKSO02,
    author = {William R. Hersh and Susan Moy and Dale Kraemer and Lynetta Sacherek and Daniel Olson},
    editor = {Ellen M. Voorhees and Lori P. Buckland},
    title = {More Statistical Power Needed: The {OHSU} {TREC} 2002 Interactive Track Experiments},
    booktitle = {Proceedings of The Eleventh Text REtrieval Conference, {TREC} 2002, Gaithersburg, Maryland, USA, November 19-22, 2002},
    series = {{NIST} Special Publication},
    volume = {500-251},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {2002},
    url = {http://trec.nist.gov/pubs/trec11/papers/ohsu.pdf},
    timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
    biburl = {https://dblp.org/rec/conf/trec/HershMKSO02.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

Rutgers Interactive Track at TREC 2002

Nicholas J. Belkin, Diane Kelly, G. Kim, Ja-Young Kim, Hyuk-Jin Lee, Gheorghe Muresan, Muh-Chyun (Morris) Tang, Xiaojun Yuan, Colleen Cool

Abstract

Two important results came out of our investigations in the TREC 2001 Interactive Track (Belkin, et al., 2002). One was that the greater the amount of interaction that searchers engaged in, the lower their satisfaction with the results of the search. We understood this to mean that interaction effort was inversely related to search satisfaction, and therefore, that making interaction more effective would lead to increased search satisfaction. The second was that performance in the searching task increased with query length. We conjectured that this was due, at least in part, to the subjects having searched using a best-match search engine (Excite1 ), as well as longer queries being better able to express the information problem. These two findings became the basis for our systems and experiments in the TREC 2002 Interactive Track. [...]

Bibtex 
@inproceedings{DBLP:conf/trec/BelkinKKKLMTYC02,
    author = {Nicholas J. Belkin and Diane Kelly and G. Kim and Ja{-}Young Kim and Hyuk{-}Jin Lee and Gheorghe Muresan and Muh{-}Chyun (Morris) Tang and Xiaojun Yuan and Colleen Cool},
    editor = {Ellen M. Voorhees and Lori P. Buckland},
    title = {Rutgers Interactive Track at {TREC} 2002},
    booktitle = {Proceedings of The Eleventh Text REtrieval Conference, {TREC} 2002, Gaithersburg, Maryland, USA, November 19-22, 2002},
    series = {{NIST} Special Publication},
    volume = {500-251},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {2002},
    url = {http://trec.nist.gov/pubs/trec11/papers/rutgers.belkin.pdf},
    timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
    biburl = {https://dblp.org/rec/conf/trec/BelkinKKKLMTYC02.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

Augmenting and Limiting Search Queries

Elaine G. Toms, Luanne Freund, Cara Li

Abstract

Web queries tend to be significantly shorter and less complex than queries used in earlier types of information systems (Jansen & Pooch, 2000; Lawrence & Giles, 1999; Spink et al, 2001). Yet, there is general belief that enriched queries and query reformulation will lead to improved results (Belkin et al, 2001). In our research we are examining the sorts of tools that could assist with the creation of enriched queries and in turn improve the search process and the user's search experience. In the work reported here we assessed the use of two types of tools: one to assist the user in targeting and, thus, restricting the query, and a second one to assist in augmenting the query. We speculated that certain types of tools are more useful for certain types of information tasks. In particular we targeted the standard informational request in which a suitable response could be culled from many different Web pages, and secondly, the ‘know-item' task, in which a specific Website exists to solve the problem. We anticipated that the tool to enable query augmentation would be more useful for informational tasks, as it would encourage amplification of the query to contain many more words and phrases that represent the information task. On the other hand, ‘know-item' searches suffer when the exact title or some exact content is not known in advance and the limiter would enable more focussed searches. [...]

Bibtex 
@inproceedings{DBLP:conf/trec/TomsFL02,
    author = {Elaine G. Toms and Luanne Freund and Cara Li},
    editor = {Ellen M. Voorhees and Lori P. Buckland},
    title = {Augmenting and Limiting Search Queries},
    booktitle = {Proceedings of The Eleventh Text REtrieval Conference, {TREC} 2002, Gaithersburg, Maryland, USA, November 19-22, 2002},
    series = {{NIST} Special Publication},
    volume = {500-251},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {2002},
    url = {http://trec.nist.gov/pubs/trec11/papers/utoronto.toms.pdf},
    timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
    biburl = {https://dblp.org/rec/conf/trec/TomsFL02.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

TREC 11 Web and Interactive Tracks at CSIRO

Nick Craswell, David Hawking, Ross Wilkinson, Mingfang Wu, James A. Thom, Trystan Upstill

Abstract

This year, the CSIRO teams participated and completed runs in two tracks: web and interactive. Our web track participation was a preliminary exploration of forms of evidence which might be useful for named page finding and topic distillation. For this reason, we made heavy use of evidence other than page content in our runs. In the interactive track, we continue to focus on answer organization issues, aiming to investigate the usefulness of the knowledge about “organizational structure” in organizing and delivering the retrieved documents. For the collection of the US government (.gov domain) web documents, we used their level two domain labels and their corresponding organization names to categorize the retrieved documents. For example, documents from the 'nih.gov' domain will be put into the 'National Institutes of Health (nih)' category. We compared this delivery method with the traditional ranked list. The preliminary results indicate that subjects achieved a significantly better performance with the category interface at the end of fifteen minutes search, however, there is no significant difference between the two methods during the first five or ten minutes. The experiment result also shows that the category interface assisted subjects answer the more complex topics as time increases.

Bibtex 
@inproceedings{DBLP:conf/trec/CraswellHWWTU02,
    author = {Nick Craswell and David Hawking and Ross Wilkinson and Mingfang Wu and James A. Thom and Trystan Upstill},
    editor = {Ellen M. Voorhees and Lori P. Buckland},
    title = {{TREC} 11 Web and Interactive Tracks at {CSIRO}},
    booktitle = {Proceedings of The Eleventh Text REtrieval Conference, {TREC} 2002, Gaithersburg, Maryland, USA, November 19-22, 2002},
    series = {{NIST} Special Publication},
    volume = {500-251},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {2002},
    url = {http://trec.nist.gov/pubs/trec11/papers/csiro.craswell.pdf},
    timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
    biburl = {https://dblp.org/rec/conf/trec/CraswellHWWTU02.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}