Bringing natural language information retrieval out of the closet

ABSTRACT

A prototype information retrieval system was developed that gives users fast and easy access to textual information. This system uses a statistical ranking methodology that allows a user to input a query using only natural language, such as a sentence or a noun phrase, with no special syntax required. The system returns a set of text titles or descriptions, ranked in order of likely relevance to the query. The user can then select one or more titles for further examination of the corresponding text. The prototype was tested by over forty users, all proficient in doing manual research in the subject area, but few proficient in doing online research. The system was very fast, providing response times on the order of one second for searching a gigabyte of data and was also very effective, retrieving at least one relevant record within the first ten records retrieved for 53 out of 68 test queries. All users were able to get satisfactory results within a short time after seeing a demonstration, and those that had never used an online retrieval system did as well as those with experience. This is in sharp contrast to Boolean based retrieval systems where continual use is necessary to obtain consistently good results.

REFERENCES

• 1: Nicholas J. Belkin , W. Bruce Croft, Retrieval techniques, Annual review of information science and technology, vol. 22, Elsevier Science Inc., New York, NY, 1987
• 2: Croft W. B. (1983). Experiments with Representation in a Document Retrieval System. <i>Information Technology: Research and Development</i>, 2(1), 1--21.
• 3: V. J. Geller , M. E. Lesk, User interfaces to information systems: choices vs. commands, Proceedings of the 6th annual international ACM SIGIR conference on Research and development in information retrieval, June 06-08, 1983, Bethesda, Maryland
• 4: Donna Williamson Harman, An experimental study of factors important in document ranking, Proceedings of the 9th annual international ACM SIGIR conference on Research and development in information retrieval, p.186-193, September 1986, Palazzo dei Congressi, Pisa, Italy [doi>10.1145/253168.253206]
• 5: D. Harmon , G. Candela, A very fast prototype retrieval system using statistical ranking, ACM SIGIR Forum, v.23 n.3-4, p.100-110, Spring 1989 [doi>10.1145/74697.74703]
• 6: Metzler D. P., Haas S. W., Cosic C. L. and Wheeler L. H. (1989). Constituent Object Parsing for Information Retrieval and Similar Text Processing Problems, <i>Journal of the American Society for Information Science</i>, 40(6), 398--423.
• 7: G. Salton, The SMART Retrieval System—Experiments in Automatic Document Processing, Prentice-Hall, Inc., Upper Saddle River, NJ, 1971
• 8: Gerard Salton , Michael J. McGill, Introduction to Modern Information Retrieval, McGraw-Hill, Inc., New York, NY, 1986
• 9: Shneiderman B., Designing Menu Selection Systems, <i>Journal of the American Society for Information Science</i>, 37(2), 57--70. <10>Sparck Jones K. (1972). A Statistical Interpretation of Term Specificity and Its Application in Retrieval. <i>Journal of Documentation</i>, 28(1), 11--20.
• 11: Sparck Jones K. (1979). Search Term Relevance Weighting Given Little Relevance Information. <i>Journal of Documentation</i>, 35(1), 30--48.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

Additional Classification:
  D. Software
  D.2 SOFTWARE ENGINEERING
      D.2.2 Design Tools and Techniques
          Subjects: User interfaces

  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Statistical software

  H. Information Systems
  H.1 MODELS AND PRINCIPLES
      H.1.2 User/Machine Systems
          Subjects: Human information processing

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Human Factors, Measurement