Natural Language Information Retrieval: TREC-7 Report
نویسندگان
چکیده
Adhoc topics were processed at GE using both automatic and manual topic expansion. We used the interactive Query Expansion Tool to expand topics with automatically generated summaries of top 30 documents retrieved by the original topic. Manual intervention was restricted to accept/reject decisions on summaries. We observed time limit of 10 minutes per topic. Automatic topics expansion was done by replacing human summary selection by an automatic procedure, which accepted only the summaries that obtained sufficiently high scores. Two sets of expanded topics (automatic and manual) were sent to Helsinki for NL processing, and then on to Rutgers for retrieval. Rankings were obtained from each stream index and then merged using a combined strategy developed at GE and SICS.
منابع مشابه
A Large-Scale Comparison of Boolean vs. Natural Language Searching for the TREC-7 Interactive Track
Studies comparing Boolean and natural language searching with actual end-users are still inconclusive. The TREC interactive track provides a consensus-developed protocol for assessing this and other useroriented information retrieval research questions. We recruited 28 experienced information professionals with library degrees to participate in this year’s TREC-7 interactive experiment. Our res...
متن کاملEvaluating Natural Language Processing Techniques in Information Retrieval: a Trec Perspective
Natural language processing techniques may hold a tremendous potential for overcoming the inadequacies of purely quantitative methods of text information retrieval, but the empirical evidence to support such predictions has thus far been inadequate, and appropriate scale evaluations have been slow to emerge. In this chapter, we report on the progress of the Natural Language Information Retrieva...
متن کاملNatural Language Information Retrieval: TREC-3 Report
In this paper we report on the recent developments in NYU’s natural language information retrieval system, especially as related to the 3rd Text Retrieval Conference (TREC-3). The main characteristic of this system is the use of advanced natural language processing to enhance the effectiveness of term-based document retrieval. The system is designed around a traditional statistical backbone con...
متن کاملNatural Language Information Retrievaltrec - 6 Report
Natural language processing techniques may hold a tremendous potential for overcoming the inadequacies of purely quantitative methods of text information retrieval, but the empirical evidence to support such predictions has thus far been inadequate, and appropriate scale evaluations have been slow to emerge. In this chapter, we report on the progress of the Natural Language Information Retrieva...
متن کاملNatural Language Information Retrieval: TIPSTER-2 Final Report
We report on the joint GE/NYU natural language information retrieval project as related to the Tipster Phase 2 research conducted initially at NYU and subsequently at GE R&D Center and NYU. The evaluation results discussed here were obtained in connection with the 3rd and 4th Text Retrieval Conferences (TREC-3 and TREC-4). The main thrust of this project is to use natural language processing te...
متن کاملDocument Retrieval Using The MPS Information Server (A Report on the TREC-7 Experiment)
This paper summarizes the results of the work conducted by FS Consulting, Inc. as part of the Seventh Text Retrieval Experiment Conference (TREC-7). We participated in two components of TREC: (1) Category C, running the Ad Hoc experiments, producing two sets of official results (fsclt7m and fsclt7a) and (2) the Very Large Collection (VLC) track, running the entire experiment, producing the requ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1998