Skip to content

Proceedings - NLP 1997

Natural Language Information Retrieval TREC-6 Report

Tomek Strzalkowski, Fang Lin, Jose Perez Carballo

Abstract

Natural language processing techniques may hold a tremendous potential for overcoming the inadequacies of purely quantitative methods of text information retrieval, but the empirical evidence to support such predictions has thus far been inadequate, and appropriate scale evaluations have been slow to emerge. In this chapter, we report on the progress of the Natural Language Information Retrieval project, a joint effort of several sites led by GE Research, and its evaluation in the 6th Text Retrieval Conferences (TREC-6).

Bibtex 
@inproceedings{DBLP:conf/trec/StrzalkowskiLC97,
    author = {Tomek Strzalkowski and Fang Lin and Jose Perez Carballo},
    editor = {Ellen M. Voorhees and Donna K. Harman},
    title = {Natural Language Information Retrieval {TREC-6} Report},
    booktitle = {Proceedings of The Sixth Text REtrieval Conference, {TREC} 1997, Gaithersburg, Maryland, USA, November 19-21, 1997},
    series = {{NIST} Special Publication},
    volume = {500-240},
    pages = {347--366},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {1997},
    url = {http://trec.nist.gov/pubs/trec6/papers/ge.ps.gz},
    timestamp = {Wed, 07 Jul 2021 01:00:00 +0200},
    biburl = {https://dblp.org/rec/conf/trec/StrzalkowskiLC97.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

Short Queries, Natural Language and Spoken Document Retrieval: Experiments at Glasgow University

Fabio Crestani, Mark Sanderson, Marcos Theophylactou, Mounia Lalmas

Abstract

This paper contains a description of the methodology and results of the three TREC submissions made by the Glasgow IR group (glair). In addition to submitting to the ad hoc task, submissions were also made to NLP track and to the SDR speech 'pre-track'. Results from our submissions reveal that some of our approaches have performed poorly (i.e. ad hoc and NLP track), but we have also had success particularly in the speech track through use of transcript merging. We also highlight and discuss a seemingly unusual result where retrieval based on the very short versions of the TREC ad hoc queries produced better retrieval effectiveness than retrieval based on more 'normal' length queries.

Bibtex 
@inproceedings{DBLP:conf/trec/CrestaniSTL97,
    author = {Fabio Crestani and Mark Sanderson and Marcos Theophylactou and Mounia Lalmas},
    editor = {Ellen M. Voorhees and Donna K. Harman},
    title = {Short Queries, Natural Language and Spoken Document Retrieval: Experiments at Glasgow University},
    booktitle = {Proceedings of The Sixth Text REtrieval Conference, {TREC} 1997, Gaithersburg, Maryland, USA, November 19-21, 1997},
    series = {{NIST} Special Publication},
    volume = {500-240},
    pages = {667--686},
    publisher = {National Institute of Standards and Technology {(NIST)}},
    year = {1997},
    url = {http://trec.nist.gov/pubs/trec6/papers/glasgow.ps.gz},
    timestamp = {Wed, 07 Jul 2021 01:00:00 +0200},
    biburl = {https://dblp.org/rec/conf/trec/CrestaniSTL97.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}