Natural language information retrieval: progress report

Natural language processing (NLP) techniques may hold a: tremendous potenti al for overcoming the inadequacies of purely quantitative methods of text i nformation retrieval, but the empirical evidence to support such prediction s has thus far been inadequate and appropriate scale evaluations have been slow to emerge. In this paper, we report on the progress of the-Natural Lan guage Information Retrieval project, a joint effort of several sites led by GE Research and its evaluation the 6th Text Retrieval Conference (TREC-6). In this paper we describe the 'stream- architecture', a method we designed to combine evidence obtained from several different document representatio ns. Some of the document representations used in the experiments described here involved the use of phrases and proper names computed using Natural La nguage Processing techniques. (C) 1999 Elsevier Science Ltd. All rights res erved.