SP500207 LSI meets TREC: A Status Report chapter S. Dumais National Institute of Standards and Technology Donna K. Harman the initial pre-processing and indexing and we will do so. We would like to use indexing methods that are as similar as possible to other automatic vector methods, so that we can examine the contribufion of LSI per se. We also now have many of the basic tools in place and should be able to conduct more experiments comparing various indexing and query matching ideas using the same underlying LSI engine. LSI was designed as a method to increase recall, especially for the short queries that users typical generate. For the TREC application we would like to explore some precision enhancing tools as well. Some of these will probably consist of more refined matching algorithms, but we also hope to move in the direction of interactive interfaces. We see this as an effective way of combining human and machine intelligence. 5. References [1] Berry, M. W. Large scale singular value computations. International Journal of Supercomputer Applications, 1992, 6(1), 13-49. [2] Cullum, J.K. and Willoughby, R.A. Lanczos algorithms for large symmetric eigenvalue computations - Vol 1 Theory, (Chapter 5: Real rectangular matrices). Brikhauser, Boston, 1985. [3] Deerwester, S., Dumais, S. T., Landauer, T. K., Furnas, 0. W. and Harshman, R. A. Indexing by latent semantic analysis. Journal of the Society for Information Science, 1990,41(6), 391-407. [4] Dumais, S. T. Improving the retrieval of information from external sources. Behavior Research Methods, Instruments and Computers, 1991,23(2), 229-236. [5] Dumais, S. T. and Schmitt, D. 0. Iterative searching in an online database. Proceedings of Human Factors Society 35th Annual Meeting, 1991, 398-402. In [6] Foltz, P. W. and Dumais, S. T. Personalized information delivery: An analysis of information filtering methods. Communications of the ACM, Dec. 1992,35(12), 51-60. [7] Furnas, 0. W., Deerwester, S., Dumais, S. T., Landauer, T. K., Harshman, R. A., Streeter, L. A., and Lochbaum, K. E. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of SIGIR, 1988, 465- 480. [8] Kane-Esrig, Y., Streeter, L., Dumais, S. T., Keese, W. and Casella, 0. The relevance density method for multi-topic queries in information retrieval. In Proceedings of the 23rd Symposium on the Inte[OCRerr]ace, E. Keramidas (Ed.), 1991,407-410. [9] Salton, 0. and McGill, M.J. Introduction to Modern Information Retrieval. McGraw- Ilill, 1983. 150