On Combining Language Models: Oracle Approach

Hacıoğlu, Kadri; Ward, W. Dixon

doi:10.21236/ada460991

Cited by 3 publications

(3 citation statements)

References 6 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, we have developed a dialog context dependent language model (LM) combining stochastic context free grammars (SCFGs) and n-grams [6,7]. Based on a spoken language production model in which a user picks a set of concepts with respective values and constructs word sequences using phrase generators associated with each concept in accordance with the dialog context, this LM computes the probability of a word, P(W), as…”

Section: Figure 2 Examples Of Class-based and Grammar-based Language Modelingmentioning

confidence: 99%

University of Colorado Dialog Systems for Travel and Navigation

Pellom¹,

Ward²,

Hansen³

et al. 2001

View full text Add to dashboard Cite

This paper presents recent improvements in the development of the University of Colorado "CU Communicator" and "CUMove" spoken dialog systems. First, we describe the CU Communicator system that integrates speech recognition, synthesis and natural language understanding technologies using the DARPA Hub Architecture. Users are able to converse with an automated travel agent over the phone to retrieve up-to-date travel information such as flight schedules, pricing, along with hotel and rental car availability. The CU Communicator has been under development since April of 1999 and represents our test-bed system for developing robust human-computer interactions where reusability and dialogue system portability serve as two main goals of our work. Next, we describe our more recent work on the CU Move dialog system for in-vehicle route planning and guidance. This work is in joint collaboration with HRL and is sponsored as part of the DARPA Communicator program. Specifically, we will provide an overview of the task, describe the data collection environment for in-vehicle systems development, and describe our initial dialog system constructed for route planning.

show abstract

Section: Figure 2 Examples Of Class-based and Grammar-based Language Modelingmentioning

confidence: 99%

University of Colorado Dialog Systems for Travel and Navigation

Pellom¹,

Ward²,

Hansen³

et al. 2001

View full text Add to dashboard Cite

show abstract

“…We have also confirmed, as others have done [18,19,20,21], that semantic knowledge extracted by a parser can be applied to rescore -best word hypotheses from the speech recognizer to improve both WER and overall end-to-end performance.…”

Section: Resultssupporting

confidence: 76%

A data-driven spoken language understanding system

Young

2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)

View full text Add to dashboard Cite

This paper presents a purely data-driven spoken language understanding (SLU) system. It consists of three major components, a speech recognizer, a semantic parser, and a dialog act decoder. A novel feature of the system is that the understanding components are trained directly from data without using explicit semantic grammar rules or fully-annotated corpus data. Despite this, the system is nevertheless able to capture hierarchical structure in user utterances and handle long range dependencies. Experiments have been conducted on the ATIS corpus and 16.1% and 12.6% utterance understanding error rates were obtained for spoken input using the ATIS-3 1993 and 1994 test sets. These results show that our system is comparable to existing SLU systems which rely on either hand-crafted semantic grammar rules or statistical models trained on fully-annotated training corpora but it has greatly reduced build cost.

show abstract

“…First, it is easier to implement since the actual implementation deals with the logarithm of probabilities. Second, its performance has been found better than the linear interpolation [11,12]. …”

Section: [Date] [Yes]) Each Concept (Except Degenerate Single Word mentioning

confidence: 99%

A concept graph based confidence measure

Hacıoğlu

Ward

2002

IEEE International Conference on Acoustics Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

In this paper, the confidence measure of a hypothesized word is derived from its posterior probability. In contrast to common approaches, in which N-best lists or word graphs/lattices are used, the posterior probabilities are derived from a concept graph. The concept graph is obtained from a word graph through a partial parsing process using semantic grammars. This approach allows us to use relatively complex and better language models along with acoustic models to compute word posterior probabilities. The language model used is comprised of stochastic context free grammars ( one for each concept) and an Ò-gram concept language model. We show that the posterior probabilities computed on concept graphs outperform those computed on word graphs when used as confidence measures. Results are presented within the context of Colorado University (CU) Communicator System; a telephone-based dialog system for making travel plans by accessing information about flights, hotels and car rentals.

show abstract

On Combining Language Models: Oracle Approach

Cited by 3 publications

References 6 publications

University of Colorado Dialog Systems for Travel and Navigation

University of Colorado Dialog Systems for Travel and Navigation

A data-driven spoken language understanding system

A concept graph based confidence measure

Contact Info

Product

Resources

About