CLARIT TREC-8 Experiments in Searching Web Data

Design and Evaluation of the CLARIT-TREC-2 System

All of the results we report in this paper follow from straightforwardapplications of base-level CLARIT processing, utilizing essentially the same CLARIT components that were employed in the CLARIT–TREC1 system. The general improvements we observe in CLARIT–TREC-2 processing are attributable tomodifications (especially simplifications) in processing steps and in the settings of system variables...

CLARIT Compound Queries and Constraint-Controlled Feedback in TREC-5 Ad-Hoc Experiments

A fundamental problem for searching over large databases in ad-hoc mode is the formulation of an effective initial query that is both comprehensive and focused. The query needs to be comprehensive enough to retrieve, on its own or enhanced by various automatic feedback techniques, relevant documents that possibly address different aspects of the topic. At the same time, it has to be focused eno...

Experiments on Chinese Text Indexing -- CLARIT TREC-5 Chinese Track Report

CLARIT TREC-8 CLIR Experiments

In the TREC-8 cross-language information retrieval (CLIR) track, we adopted the approach of using machine translation to prepare a source-language query for use in a target-language retrieval task. We empirically evaluated (1) the effect of pseudo relevance feedback on retrieval performance with two feedback vector length control methods in CLIR and (2) the effect of multilingual data merging e...

Evaluation of Syntactic Phrase Indexing -- CLARIT NLP Track Report

The CLARIT NLP track e ort is focused on evaluating the usefulness of syntactic phrases for document indexing. The CLARIT system has several NLP techniques integrated with the vector space retrieval model [Evans et al. 91, Evans et al. 95]. The NLP techniques used in CLARIT include morphological analysis, robust noun-phrase parsing, and automatic construction of rst order thesauri, among others...