Page: 1... 63 64 65 66 67 68 69 70 71... 82
Hits 1.321 – 1.340 of 1.629
1321 |
BBN PLUM: MUC-3 Test Results and Analysis
|
|
|
|
In: DTIC (1991)
|
|
Abstract:
Perhaps the most important facts about our participation in MUC-3 reflect our starting point and goals. In March, 1990, we initiated a pilot study on the feasibility and impact of applying statistical algorithms in natural language processing. The experiments were concluded in March, 1991 and lead us to believe that statistical approaches can effectively improve knowledge-based approaches [Weishedel, et al., 1991a, Weischedel, Meteer, and Schwartz, 1991]. Due to nature of that effort, we had focused on many well-defined algorithm experiments. We did not have a complete message processing system; nor was the pilot study designed to create an application system. For the Phase I evaluation, we supplied a module to New York University. At the time of the Phase I Workshop (12-14 February 1991) we decided to participate in MUC with our own entry. The Phase I Workshop provided invaluable insight into what other sites were finding successful in this particular application. On 25 February, we started an intense effort not just to be evaluated on the FBIS articles, but also to create essential components (e.g., discourse component and template generator) and to integrate all components into a complete message processing system. Although the timing of the Phase II test (6-12 May) was hardly ideal for evaluating our site's capabilities, it was ideally timed to serve as a benchmark prior to starting a four year plan for research and development in message understanding. Because of this, we were determined to try alternatives that we believed would be different than those employed by other groups, wherever time permitted. These are covered in the next section.Our results were quite positive, given these circumstances. Our max-tradeoff version achieved 45% recall and 52% precision with 22% overgenerating (See Figure 2). PLUM can be run in several modes, trading off recall versus precision and overgeneration. ; Presented at the Message Understanding Conference (Third) (MUC-3), held in San Understanding Conference (Third) (MUC-3), held in San Diego, CA on 21-23 May 1991. Pub. in the Proceedings of the Message Understanding Conference (Third) (MUC-3), 1991. Paper M91-1006. Sponsored in part by the Defense Advanced Research Projects Agency (DARPA).
|
|
Keyword:
*INFORMATION RETRIEVAL; *KNOWLEDGE BASED SYSTEMS; *LANGUAGE TRANSLATION; *MATHEMATICAL MODELS; *MESSAGE PROCESSING; *MESSAGE UNDERSTANDING; *NATURAL LANGUAGE; *PROBABILISTIC LANGUAGE UNDERSTANDING MODELS; ALGORITHMS; COMPUTATIONAL LINGUISTICS; Cybernetics; Information Science; Linguistics; MARKOV MODELS; MITFP(MIT FAST PARSER); PARSERS; PARTIAL UNDERSTANDING; PHRASE STRUCTURE GRAMMARS; PILOT STUDIES; PLUM(PROBABILISTIC LANGUAGE UNDERSTANDING MODEL); PRECISION; PROBABILITY; RECALL; SEMANTIC INTERPRETER; SEMANTICS; STATISTICAL LANGUAGE MODELS; SYMPOSIA; SYNTAX; TEMPLATES; TEST AND EVALUATION; TEXT PROCESSING; WORD TAGGING; WORKSHOPS
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA460729 http://www.dtic.mil/docs/citations/ADA460729
|
|
BASE
|
|
Hide details
|
|
1322 |
Augmented Role Filling Capabilities for Semantic Interpretation of Spoken Language
|
|
|
|
In: DTIC (1991)
|
|
BASE
|
|
Show details
|
|
1323 |
Procedural Text: Predictions of Importance Ratings and Recall by Models of Text Comprehension
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
1324 |
Continued Performance Assessment Methodology (PAM) Research (VORPET). Refinement and Implementation of the JWGD3 MILPERF-NAMRL Multidisciplinary Performance Test Battery (NMPTB).
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
1325 |
Adaptive Natural Language Processing
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
1326 |
Natural Language Processing Systems Evaluation Workshop Held in Berkely, California on 18 June 1991
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
1327 |
Pan I Version 4.0: An Introduction For Users
|
|
|
|
In: DTIC (1991)
|
|
BASE
|
|
Show details
|
|
1328 |
Global Optimization of Digital Circuits.
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
1333 |
Diagnostische Grammatiktests : Planung, Konstruktion und Anwendung einer Testbatterrie zur Diagnose sprachlicher Defizite bei heterogenen Schülerpopulationen am Beispiel der Einstufungsdiagnose für die Jahrgangsstufe 11.1
|
|
|
|
BLLDB
|
|
UB Frankfurt Linguistik
|
|
Show details
|
|
1337 |
Research in Natural Language Processing
|
|
|
|
In: DTIC AND NTIS (1990)
|
|
BASE
|
|
Show details
|
|
1338 |
Software Technology for Adaptable, Reliable Systems (STARS): Peer Review Capability Description
|
|
|
|
In: DTIC AND NTIS (1990)
|
|
BASE
|
|
Show details
|
|
1339 |
Management and Evaluation of Interactive Dialog in the Air Travel Domain
|
|
|
|
In: DTIC (1990)
|
|
BASE
|
|
Show details
|
|
1340 |
Computer-Based Instruction Authoring Tools System (CATS): User's Manual.
|
|
|
|
In: DTIC AND NTIS (1990)
|
|
BASE
|
|
Show details
|
|
Page: 1... 63 64 65 66 67 68 69 70 71... 82
|
|