| 1 |
BBN: Description of the PLUM System as Used for MUC-6
|
|
|
|
In: DTIC (1995)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
BBN: Description of the PLUM System as Used for MUC-5
|
|
|
|
In: DTIC (1993)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
BBN's PLUM Probabilistic Language Understanding System
|
|
|
|
In: DTIC (1993)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
A Practical Methodology for the Evaluation of Spoken Language Systems
|
|
|
|
In: DTIC (1992)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
BBN: Description of the PLUM System as Used for MUC-4
|
|
|
|
In: DTIC (1992)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
BBN: Description of the PLUM System as Used for MUC-3
|
|
|
|
In: DTIC (1991)
|
|
Abstract:
Traditional approaches to the problem of extracting data from texts have emphasized handcrafted linguistic knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of a DARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques. Our research and development goals are * more rapid development of new applications, * the ability to train (and re-train) systems based on user markings of correct and incorrect output, * more accurate selection among interpretations when more than one is found, and * more robust partial interpretation when no complete interpretation can be found. We have previously performed experiments on components of the system with texts from the Wall Street Journal, however, the MUC-3 task is the first end-to-end application of PLUM. MI components except parsing were developed in the last 5 months, and cannot therefore be considered fully mature. The parsing component, the MIT Fast Parser [4], originated outside BBN and has a more extensive history prior to MUC-3. A central assumption of our approach is that in processing unrestricted text for data extraction, a non-trivial amount of the text will not be understood. As a result, all components of PLUM are designed to operate on partially understood input, taking advantage of information when available, and not failing when information is unavailable. ; Presented at the Conference on Message Understanding (3rd) held in San Diego, CA on 21-23 May 1991. Pub. in the Proceedings of the Conference on Message Understanding (3rd), 1991.
|
|
Keyword:
*INFORMATION RETRIEVAL; *KNOWLEDGE BASED SYSTEMS; *LANGUAGE TRANSLATION; *MATHEMATICAL MODELS; *MESSAGE UNDERSTANDING; *PROBABILISTIC LANGUAGE UNDERSTANDING MODELS; *TEXT PROCESSING; ACCURACY; COMPUTATIONAL LINGUISTICS; COMPUTER ARCHITECTURE; Cybernetics; DATA EXTRACTION; DISCOURSE PROCESSING; Information Science; Linguistics; MACHINE TRANSLATION; PARSERS; PLUM(PROBABILISTIC LANGUAGE UNDERSTANDING MODEL); PROBABILITY; RULE BASED SYSTEMS; SEMANTIC INTERPRETER; SEMANTICS; SYMPOSIA; TEMPLATES; TRAINING
|
|
URL: http://www.dtic.mil/docs/citations/ADA460678
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA460678
|
|
BASE
|
|
Hide details
|
|
|
| 10 |
Adaptive Natural Language Processing
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
|
|
|
