E-LIS, Eprints in Library and Information Science Homepage E-LIS, Eprints in Library and Information Science
   home   |   about   |   search   |   browse   |   register   |   registered users area   |   help   |   FAQ   |   JITA   

Learning Similarity Functions
in Information Retrieval

Mandl, Thomas (1998) Learning Similarity Functions
in Information Retrieval. In Zimmermann, Hans-Jürgen, Eds. Proceedings EUFIT ‘98. 6th European Congress on Intelligent Techniques and Soft Computing. ,, pp. 771-775, Aachen, Germany.

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

Most models for Information Retrieval (IR) using neural networks are simple spreading activation models.
Some of them were successfully applied to real world document collections. Nevertheless, they do not exploit the
subsymbolic paradigma of neural processing. In this paper a model using a simple backpropagation network for IR is
proposed. The COSIMIR model implements the central process in IR. It is a backpropagation network which
calculates the similarity between a document and a query representation. The similarity function is learned through
examples. Hence, it implements a cognitive similarity function. The first evaluation demonstrates that COSIMIR
works well for short vectors.

Keywords:neural networks, information retrieval
Subjects:I. Information treatment for information services > IB. Content analysis (A and I, class.)
L. Information technology and library technology. > LM. Automatic text retrieval.
L. Information technology and library technology. > LS. Search engines.
ID Code:7092
Deposited By:Mandl, Thomas
Deposited On:29 August 2006
All fields:Show all fields

Bordogna, Gloria; Pasi, Gabriella; Petrosino, Alfredo (1996): Relevance Feedback Based on a Neural Network. In: Zimmermann (ed.) (1996). pp. 846-849.

Boughanem, M.; Soulé-Dupuy, C. (1997): MercureO2: adhoc and routing tasks. In: Harman 1997.

Caid, William R.; Dumais, Susan T.; Gallant, Stephen I. (1995): Learned Vector-Space Models for Document Retrieval. In: Informatin Processing & Management. vol. 31 (3).1995. pp. 419-429.

Chen, Hsinchun (1995): Machine Learning for Information Rerieval: Neural Networks, Symbolic Learing, and Genetic Algorithmus. In: Journal of the American Society for Information Science. JASIS vol. 46(3). pp. 194-216.

Crestani, Fabio; Rijsbergen, Cornelis van (1997): A Model for Adaptive Information Retrieval. In: Journal of Intelligent Information Systems.

Doszkocs, T.E.; Reggia, J.; Lin, X. (1990): Connectionist Models and Information Retrieval. In: Annual Review of Information Science and Technology (ARIST), vol. 25. pp. 209-260.

Dumais, Susan (1994): Latent Semantic Indexing (LSI) and TREC-2. In: Harman 1994. pp. 105-115.

Escobedo, Richard; Smith, Scott; Caudell, Thomas (1993): A Neural Information Retrieval System. In: International Journal of Advanced Manufacturing Technology vol. 8 (4). pp. 269-274.

Harman, Donna (ed.) (1996): The Fourth Text Retrieval Conference (TREC-4).

Harman, Donna (ed.) (1997): The Fifth Text Retrieval Conference (TREC-5).

Harman, Donna (ed.) (1998): The Sixth Text Retrieval Conference (TREC-6).

Hartung, Joachim (1984): Lehr- und Handbuch der angewandten Statistik. München, Wien.

Jones, William; Furnas, George (1987): Pictures of Relevance: A geometric Analysis of Similarity Measures. In:

Journal of the American Society for Information Science. JASIS vol. 38(6). pp. 420-442.

Krause, Jürgen; Christa Womser-Hacker (eds.) (1997): Vages Information Retrieval und graphische Benutzungsoberflächen - Beispiel Werkstoffinformation. Konstanz.

Kwok, K.L.; Grunfeld, L. (1996): TREC-4 Ad-Hoc, Routing Retrieval and Filtering Experiments using PIRCS. In: Harman 1996.

Layaida, Redouane; Caron, Armand (1994): Applications of the Backpropagation Algorithm to an Information Retrieval System. In: Proceedings of the RIAO ‘94 (Rechenche d’Information assistée par Ordinateur). Rockfeller University. New York. pp. 161-171.

Ludwig, Michaela; Mandl, Thomas (1997): Ähnlichkeit von Werkstoffen: Die Anwendung unterschiedlicher Wissensmodellierungstechniken für eine intelligente Komponente. In: Krause/Womser-Hacker (1997). pp. 169-184.

Mandl, Thomas (1998): Das COSIMIR-Modell: Information Retrieval mit Neuronalen Netzen. Informationszentrum Sozialwissenschaften Bonn, Arbeitsbericht, Feb. 1998.

Mothe, Josiane (1994): Search Mechanisms Using a Neural Network Model. In: Proceedings of the RIAO 94 (Recherche d’Information assistée par Ordinateur). Rockfeller University. New York. pp. 275-294.

Salton, Gerard; Buckley, Chris (1988): On the Use of Spreading Activation Methods in Automatic Information Retrieval. In: Chiaramella, Yves (ed.): 11th Int. Conf. on Information Retrieval. New York 1988. pp. 147-160.

Scheinost, Ulrich; Haas, Hansjörg; Krause, Jürgen; Lindlbauer, Jürg (eds.) (1998): Marktanalyse und Marktprognose: Das ZVEI Verbandsinformationssystem ELVIRA. Bonn.

Wilkinson, Ross; Hingston, P. (1992): Incorporating the vector space model in a neural network used for document retrieval. In: Library HiTech News vol. 10 (1-2). pp. 69-75.

Womser-Hacker, Christa (1996): Das MIMOR-Modell. Mehrfachindexierung zur dynamischen Methoden-Objekt-Relationierung im Information Retrieval. Habilitationsschrift. Universität Regensburg, Informationswissenschaft.

Zimmermann, Hans-Jürgen (ed.): EUFIT ‘96. 4th European Congress on Intelligent Techniques and Soft Computing. Aachen, Germany, 02.-05. Sept. 1996.

Archive Staff Only: edit this record

   home   |   about   |   search   |   browse   |   register   |   registered users area   |   help   |   FAQ   |   JITA   

Send comments and questions to      |     E-LIS is hosted by AEPIC at CILEA      |     Powered by GNU Eprints software