Abstract
The authors describe the PUNDIT (Prolog Understanding of Integrated Text) text-understanding system, which is designed to analyze and construct representations of paragraph-length text. PUNDIT is implemented in Quintus Prolog, and consists of distinct lexical, syntactic, semantic, and pragmatic components. Each component draws on one or more sets of data, including a lexicon, a broad-coverage grammar of English, semantic verb decompositions, rules mapping between syntactic and semantic constituents, and a domain model. Modularity, careful separation of declarative and procedural information, and separation of domain-specific and domain-independent information all contribute to a system which is flexible, extensible and portable. Versions of PUNDIT are now running in five domains, including four military and one medical.
| Original language | English (US) |
|---|---|
| Title of host publication | Proc Annu AI Syst Gov Conf |
| Editors | James H. Antonisse, John W. Benoit, Barry G. Silverman |
| Pages | 234-243 |
| Number of pages | 10 |
| State | Published - Dec 1 1989 |
| Event | Proceedings of the Annual AI Systems in Government Conference - Washington, DC, USA Duration: Mar 27 1989 → Mar 31 1989 |
Publication series
| Name | Proc Annu AI Syst Gov Conf |
|---|
Other
| Other | Proceedings of the Annual AI Systems in Government Conference |
|---|---|
| City | Washington, DC, USA |
| Period | 3/27/89 → 3/31/89 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
Cite this
}
PUNDIT : natural-language processing system. / Hirschman, Lynette; Palmer, Martha; Dowding, John; Dahl, Deborah; Linebarger, Marcia; Passonneau, Rebecca Jane; Lang, Francois Michel; Ball, Catherine; Weir, Carl.
Proc Annu AI Syst Gov Conf. ed. / James H. Antonisse; John W. Benoit; Barry G. Silverman. 1989. p. 234-243 (Proc Annu AI Syst Gov Conf).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - PUNDIT
T2 - natural-language processing system.
AU - Hirschman, Lynette
AU - Palmer, Martha
AU - Dowding, John
AU - Dahl, Deborah
AU - Linebarger, Marcia
AU - Passonneau, Rebecca Jane
AU - Lang, Francois Michel
AU - Ball, Catherine
AU - Weir, Carl
PY - 1989/12/1
Y1 - 1989/12/1
N2 - The authors describe the PUNDIT (Prolog Understanding of Integrated Text) text-understanding system, which is designed to analyze and construct representations of paragraph-length text. PUNDIT is implemented in Quintus Prolog, and consists of distinct lexical, syntactic, semantic, and pragmatic components. Each component draws on one or more sets of data, including a lexicon, a broad-coverage grammar of English, semantic verb decompositions, rules mapping between syntactic and semantic constituents, and a domain model. Modularity, careful separation of declarative and procedural information, and separation of domain-specific and domain-independent information all contribute to a system which is flexible, extensible and portable. Versions of PUNDIT are now running in five domains, including four military and one medical.
AB - The authors describe the PUNDIT (Prolog Understanding of Integrated Text) text-understanding system, which is designed to analyze and construct representations of paragraph-length text. PUNDIT is implemented in Quintus Prolog, and consists of distinct lexical, syntactic, semantic, and pragmatic components. Each component draws on one or more sets of data, including a lexicon, a broad-coverage grammar of English, semantic verb decompositions, rules mapping between syntactic and semantic constituents, and a domain model. Modularity, careful separation of declarative and procedural information, and separation of domain-specific and domain-independent information all contribute to a system which is flexible, extensible and portable. Versions of PUNDIT are now running in five domains, including four military and one medical.
UR - http://www.scopus.com/inward/record.url?scp=0024860969&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0024860969&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0024860969
SN - 0818619341
T3 - Proc Annu AI Syst Gov Conf
SP - 234
EP - 243
BT - Proc Annu AI Syst Gov Conf
A2 - Antonisse, James H.
A2 - Benoit, John W.
A2 - Silverman, Barry G.
ER -