2 |
Advanced Capabilities for Evidence Extraction (ACEE)
|
|
|
|
In: DTIC AND NTIS (2004)
|
|
BASE
|
|
Show details
|
|
3 |
The Bible, Truth, and Multilingual OCR Evaluation
|
|
|
|
In: DTIC (1998)
|
|
BASE
|
|
Show details
|
|
4 |
Adaptive Statistical Language Modeling; A Maximum Entropy Approach
|
|
|
|
In: DTIC AND NTIS (1994)
|
|
Abstract:
Language modeling is the attempt to characterize, capture and exploit regularities in natural language. In statistical language modeling, large amounts of text are used to automatically determine the model's parameters. Language modeling is useful in automatic speech recognition, machine translation, and any other application that processes natural language with incomplete knowledge. In this thesis, I view language as an information source which emits a stream of symbols from a finite alphabet (the vocabulary). The goal of language modeling is then to identify and exploit sources of information in the language stream, so as to minimize its perceived entropy. Most existing statistical language models exploit the immediate past only. To extract information from further back in the document's history, I use trigger pairs as the basic information bearing elements. This allows the model to adapt its expectations to the topic of discourse. Next, statistical evidence from many sources must be combined. Traditionally, linear interpolation and its variants have been used, but these are shown here to be seriously deficient. Instead, I apply the principle of Maximum Entropy (ME). Each information source gives rise to a set of constraints, to be imposed on the combined estimate. The intersection of these constraints is the set of probability functions which are consistent with all the information sources. The function with the highest entropy within that set is the NE solution. Language modeling, Adaptive language modeling, Statistical language modeling, Maximum entropy, Speech recognition.
|
|
Keyword:
*NATURAL LANGUAGE; *SPEECH RECOGNITION; ALGORITHMS; AUTOMATIC; BEARINGS; COMPUTER AIDED INSTRUCTION; COMPUTER APPLICATIONS; Cybernetics; ENTROPY; ERRORS; ESTIMATES; INTERPOLATION; LANGUAGE TRANSLATION; Linguistics; MACHINE TRANSLATION; PARAMETERS; PROBABILITY DISTRIBUTION FUNCTIONS; STATISTICS; SYMBOLS; TEST AND EVALUATION; THESES; VOCABULARY
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA281027 http://www.dtic.mil/docs/citations/ADA281027
|
|
BASE
|
|
Hide details
|
|
5 |
Comparative Experiments on Large Vocabulary Speech Recognition
|
|
|
|
In: DTIC (1993)
|
|
BASE
|
|
Show details
|
|
6 |
Dialog Structure and Plan Recognition in Spontaneous Spoken Dialog
|
|
|
|
In: DTIC AND NTIS (1993)
|
|
BASE
|
|
Show details
|
|
7 |
Methods for Parallelizing Search Paths in Phrasing
|
|
|
|
In: DTIC AND NTIS (1993)
|
|
BASE
|
|
Show details
|
|
8 |
GE-CMU: Description of the Tipster/Shogun System as Used for MUC-4
|
|
|
|
In: DTIC (1992)
|
|
BASE
|
|
Show details
|
|
10 |
Development of a Spoken Language System
|
|
|
|
In: DTIC AND NTIS (1992)
|
|
BASE
|
|
Show details
|
|
13 |
Speaker-Independent Connected Speech.
|
|
|
|
In: DTIC AND NTIS (1987)
|
|
BASE
|
|
Show details
|
|
14 |
An Evaluation of Process and Experiment Automation Realtime Language (PEARL)
|
|
|
|
In: DTIC AND NTIS (1977)
|
|
BASE
|
|
Show details
|
|
|
|