Proceedings of the Workshop on Human Language Technology - HLT '94 1994
DOI: 10.3115/1075812.1075874
|View full text |Cite
|
Sign up to set email alerts
|

Statistical language processing using hidden understanding models

Abstract: This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models derives from statistical models used in speech recognition, especially the use of hidden Markov models. These techniques are applied to the central problem of determining meaning directly from a sequence of spoken or written words. We present an overall description of the hidden understanding methodology, and discuss some of the crit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
17
0

Year Published

1998
1998
2015
2015

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 31 publications
(17 citation statements)
references
References 5 publications
0
17
0
Order By: Relevance
“…A tree structured meaning representation was proposed in the Hidden Understanding Model (HUM) [16]. An example of this representation is shown in Figure 2.…”
Section: Figure 2 -An Example Hierarchical Semantic Representation Fomentioning
confidence: 99%
“…A tree structured meaning representation was proposed in the Hidden Understanding Model (HUM) [16]. An example of this representation is shown in Figure 2.…”
Section: Figure 2 -An Example Hierarchical Semantic Representation Fomentioning
confidence: 99%
“…Generative models were exploited by Seneff (1989) and Miller et al (1994), who used stochastic grammars for CSL. Other discriminative models followed such preliminary work, e.g., (Rubinstein and Hastie, 1997;Santafé et al, 2007;Raymond and Riccardi, 2007).…”
Section: Related Workmentioning
confidence: 99%
“…In such a task where a lot of data have been collected, the use of a statistical language model -gram) is typical and can be effective. Moreover, statistical concept modeling [3], [4] has been studied and demonstrated to be a viable way to model semantics in domain-restrictive tasks. In actual situations, however, it is not realistic to assume that a large amount of dialogue data are available for training such models for every single application.…”
mentioning
confidence: 99%