Approaches to passage retrieval in full text information systems

ABSTRACT

Large collections of full-text documents are now commonly used in automated information retrieval. When the stored document texts are long, the retrieval of complete documents may not be in the users' best interest. In such circumstance, efficient and effective retrieval results may be obtained by using passage retrieval strategies designed to retrieve text excerpts of varying size in response to statements of user interest. New approaches are described in this study for implementing selective passage retrieval systems, and identifying text passages responsive to particular user needs. An automated encyclopedia search system is used to evaluate the usefulness of the proposed methods.

REFERENCES

• 1: H.P. Luhn, The Automatic Creation of Literature Abstracts, IBM Journal of Research and Development 2:2, April 1958, 159-165.
• 2: H. P. Edmundson , R. E. Wyllys, Automatic abstracting and indexing—survey and recommendations, Communications of the ACM, v.4 n.5, p.226-234, May 1961 [doi>10.1145/366532.366545]
• 3: H. P. Edmundson, Problems in automatic abstracting, Communications of the ACM, v.7 n.4, p.259-263, April 1964 [doi>10.1145/364005.364088]
• 4: J.E. Rush, R. Salvador, and A. Zamora, Automatic Abstracting and Indexing- Production of Indicative Abstracts by Application of Contextual Inference and Syntactic Coherence Criteria, Journal of the ASIS, 22:4, July-August 1964, 260-274.
• 5: L.L. Earl, Experiments in Automatic Extracting and Indexing, Information Storage and Retrieval, 6:4, October 1970, 313-334.
• 6: P.B. Baxendale, Man-Made Index for Technical Literature- An Experiment, IBM Journal of Research and Development, 2:4, 1958, 354-361.
• 7: C. D. Paice, The automatic generation of literature abstracts: an approach based on the identification of self-indicating phrases, Proceedings of the 3rd annual ACM conference on Research and development in information retrieval, p.172-191, June 23-27, 1980, Cambridge, England
• 8: C. D. Paice, Constructing literature abstracts by computer: techniques and prospects, Information Processing and Management: an International Journal, v.26 n.1, p.171-186, 1990 [doi>10.1016/0306-4573(90)90014-S]
• 9: J. O'Connor, Retrieval of Answer Sentences and Answer Figures by Text Searching, Information Processing and Management, 11:5/7, 1975, 155- 164.
• 10: J. O'Connor, Data Retrieval by Text Searching, Journal of Chemical Information and Computer Sciences, 17, 1977, 181-186.
• 11: j. O'Connor, Answer Passage Retrieval by Text Searching, Journal of the American Society }'or Information Science, 32:4, July 1980, 227-239.
• 12: U. Hahn and U. Reimer, Entwurfsprinzipien und Architektur des Textkondensierungssystems TOPIC, Report TOPIC 14/85, University of t(onstanz, Germany, April 1985.
• 13: U. Reimer and U. Hahn, Text Condensation as Knowledge Base Abstraction, Report MIP-8723, University of Passau, Germany, December 1987.
• 14: J.W. McInroy, A Concept Vector Representation of the Paragraphs in a Document Applied to Automatic Extracting, Report TR78-001, Computer Science Department, University of North Carolina, Chapel Hill, NC, 1978.
• 15: Gerard Salton, Automatic text processing: the transformation, analysis, and retrieval of information by computer, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989
• 16: L. Wittgenstein, Philosophical Investigations, Basil Blackwell and Mort Ltd., Oxford, England, 1953.
• 17: G. Salton and C. Buckley, Global Text Matching for Information Retrieval, Science 253:5023, 30 August 1991, 1012-1015.
• 18: Gerard Salton , Chris Buckley, Automatic text structuring and retrieval-experiments in automatic encyclopedia searching, Proceedings of the 14th annual international ACM SIGIR conference on Research and development in information retrieval, p.21-30, October 13-16, 1991, Chicago, Illinois, United States [doi>10.1145/122860.122863]
• 19: Funk and Wagnalls New Encyclopedia, Funk and Wagnalls, New York, 1979, 29 volumes, 25,000 encyclopedia articles, ranging in length from one line for cross-reference articles to 150 pages of text for the article entitled "United States of America".

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Search process

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Text analysis

General Terms:
Design, Languages, Performance