Statistical language processing using hidden understanding models

Miller, S.L.; Schwartz, Richard; Bobrow, Robert; Ingria, Robert

doi:10.3115/1075812.1075874

Cited by 31 publications

(17 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

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%

Spoken language understanding: a survey

Mori

2007

2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU)

View full text Add to dashboard Cite

show abstract

“…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%

Spoken language understanding: a survey

Mori

2007

2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU)

View full text Add to dashboard Cite

show abstract

“…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%

Semantic Kernels for Semantic Parsing

Saleh¹,

Moschitti²,

Nakov³

et al. 2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We present an empirical study on the use of semantic information for Concept Segmentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses output by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of semantic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures outperform state-of-the-art rerankers.

show abstract

“…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%

Flexible speech understanding based on combined key-phrase detection and verification

Kawahara

Lee²,

Juang³

1998

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

We propose a novel speech understanding strategy based on combined detection and verification of semantically tagged key-phrases in spontaneous spoken utterances. Key-phrases are defined in a top-down manner so as to constitute semantic slots. Their detection directly leads to robust understanding. A phrase network realizes both a wide coverage and a reasonable constraint for detection. A subword-based verifier is then incorporated to reduce false alarms in detection and attach confidence measures of the detected phrases. This set of phrase confidence measures, when incorporated in a spoken dialogue system, forms a basis for designing intelligent speech interfaces that accept only verified key-phrases and reprompt users to clarify unspecified or unrecognized portions. Several forms of confidence measures based on subword-level tests are investigated. The proposed approach was tested on field data collected from realworld trial applications. The combined detection and verification strategy drastically improves the accuracy in handling out-ofgrammar utterances over the conventional decoding approaches while maintaining the performance for in-grammar utterances.

show abstract

Statistical language processing using hidden understanding models

Cited by 31 publications

References 5 publications

Spoken language understanding: a survey

Spoken language understanding: a survey

Semantic Kernels for Semantic Parsing

Flexible speech understanding based on combined key-phrase detection and verification

Contact Info

Product

Resources

About