Abstract | ||
---|---|---|
This paper describes a system for question answering using semi-structured metadata, QuASM (pronounced "chasm"). Question answering systems aim to improve search performance by providing users with specific answers, rather than having users scan retrieved documents for these answers. Our goal is to answer factual questions by exploiting the structure inherent in documents found on the World Wide Web (WWW). Based on this structure, documents are indexed into smaller units and associated with metadata. Transforming table cells into smaller units associated with metadata is an important part of this task. In addition, we report on work to improve question classification using language models. The domain used to develop this system is documents retrieved from a crawl of www.fedstats.gov. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1145/544220.544228 | JCDL |
Keywords | Field | DocType |
question classification,language model,factual question,semi-structured data,transforming table cell,smaller unit,semi-structured metadata,question answering,important part,world wide web,question answering system,semi structured data,document retrieval,indexation,metadata | Semi-structured data,Metadata,Metadata repository,World Wide Web,Question answering,Information retrieval,Computer science,Language model | Conference |
ISBN | Citations | PageRank |
1-58113-513-0 | 49 | 3.86 |
References | Authors | |
7 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
David Pinto | 1 | 245 | 19.82 |
Michael Branstein | 2 | 49 | 3.86 |
Ryan Coleman | 3 | 50 | 4.23 |
W. Bruce Croft | 4 | 17812 | 2796.94 |
Matthew King | 5 | 64 | 5.95 |
Wei Li | 6 | 318 | 30.46 |
Xing Wei | 7 | 1141 | 60.87 |