Using Query Zoning and Correlation Within SMART: TREC 5.
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The major focus this year is on zoning different parts of an initial retrieval ranking, and treating each type of query zone differently as processing continues, as well as experiment with dynamic phrasing.
Abstract
The Smart information rtrieval project emphasizes completely automatic approaches to the understanding and retrieval of large quantities of text. We continue our work in TREC 5, performaing runs in the routing, ad-hoc, and foreign language environments. The major focus this year is on zoning different parts of an initial retrieval ranking, and treating each type of query zone differently as processing continues. We also experiment with dynamic phrasing, seeing which words co-occur with originak query words in documents judged relevant. Exactly the same procedure is used for foreign language environments as for English; our tenet is that good information retrieval techniques are powerful than linguistic knowledge