W. Minker, S. Bennacef, and J.L. Gauvin. A Stochastic Case Frame Approach for Natural Language Understanding. In Proceedings 4th International Conference on Spoken Language Processing, pages 1013-16, Philadelphia, 1996. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Issues In The Development Of A Stochastic Speech.. - Lefèvre.. (Correct)
....In order to decrease the development cost, this work investigates the performance of stochastic understanding models with two parameters: the use of automatically segmented data and the use of automatically learned lexical normalisation rules. 1. INTRODUCTION In stochastic understanding [1, 2, 3], models are automatically trained on a large amount of data annotated with concepts (seman tic units) Despite the advantages offered by this approach over rule based approaches, for instance less extensive human expertise is required, the emergence of stochastic understanding is hindered by ....
W. Minker, S. Bennacef, and J.-L. Gauvain. A stochastic case frame approach for natural language understanding. In ICSLP, 1996.
Evaluation Methodologies for Interactive Speech Systems - Minker (1998) (3 citations) Self-citation (Minker) (Correct)
.... score reference evaluation score extraction reference reference evaluation response word sequence semantic analysis response score sequence response concept value evaluation concept value system all label Figure 3: Multi level evaluation of the natural language understanding component (Minker et al. 1996). than deletions or insertions. However, the above categories do not always allow for an easy evaluation of a speech recognizer, notably for connected words or continuous speech. A substitution may be interpreted as an deletion followed by an insertion. For the evaluation of speech recognition ....
....sites. The scores therefore only indicate component performance to developers of a spoken language system. Evaluating the semantic representation at various levels enables a more refined error analysis. An example for a multi level strategy for natural language system evaluation is described in (Minker et al. 1996) for the ATIS task. A stochastic method for the semantic analysis component of a spoken language system for ATIS was developed and compared to a rule based method (Bennacef et al. 1994; Minker, 1995) Both implementations are based on a case grammar formalism (Bruce, 1975) which identifies ....
[Article contains additional citation context not shown here]
W. Minker, S.K. Bennacef, and J.L. Gauvain (1996), "A Stochastic Case Frame Approach for Natural Language Understanding," Proc. ICSLP, pp. 1013--1016.
Semantic Analysis for Automatic Spoken Language Translation and.. - Minker (1998) (1 citation) Self-citation (Minker) (Correct)
No context found.
W. Minker, S.K. Bennacef, and J.L. Gauvain (1996b), "A Stochastic Case Frame Approach for Natural Language Understanding, " Proc. ICSLP, October, pp. 1013--1016.
Evaluating Parses for Spoken Language Dialogue Systems - Minker, Chase Self-citation (Minker) (Correct)
....system: complete set of cases of the application Figure 1: Semantic case grammar formalism. This paper is about how the developers of two specific parsers rely on the evaluation of parses during development and test phases. The first of these is a STOCHASTIC PARSER described in (Minker, 1997; Minker, 1996). The second is the PHOENIX parser, developed at Carnegie Mellon University (Ward et al. 1995) which combines rule based and stochastic parsing methods. Both parsers rely on case frame grammars as their fundamental representation scheme, and each employs robust parsing techniques. Both have been ....
.... seat with the least expensive fare) Minker, 1997) semantic sequences sequences word TRAINING TESTING DECODING sequence sequence word semantic parameter estimator model stochastic semantic decoder Figure 3: Overview of the STOCHASTIC PARSER using a stochastic method for the semantic analysis (Minker, 1996). There are two main processing steps in the development of such a model: 1. During training, the parameter estimator establishes the model parameters from a large number of preprocessed word sequences and the corresponding semantic label sequences. The sequential representation of semantic labels ....
[Article contains additional citation context not shown here]
W. Minker, S.K. Bennacef, and J.L. Gauvain (1996), "A Stochastic Case Frame Approach for Natural Language Understanding," Proc. ICSLP, October, pp. 1013--1016.
Spoken Language Processing in a Multilingual Context - Lamel, Adda-Decker, Gauvain, .. (1996) Self-citation (Gauvain) (Correct)
.... vocabulary, speaker independent continuous speech dictation [5, 4, 2, 3] the development of multilingual spoken language systems [19, 10, 8] automatic speaker and language identification [20, 13, 21] Investigations in automatic prosodic feature extraction [14] and stochastic concept modeling [11] aim at different levels of representation, to improve spontaneous speech recognition and understanding. Our present read speech recognition systems achieve comparable recognition accuracies in different European languages (French, German and British English) and in American English [4] They are ....
W. Minker, S. Bennacef, J.L. Gauvain, "A Stochastic Case Frame Approach for Natural Language Understanding," ICSLP'96.
Stochastically-Based Natural Language Understanding Across Tasks.. - Minker (1997) (1 citation) Self-citation (Minker) (Correct)
....on both tasks. 1. INTRODUCTION In this paper, we report on our experience in porting a stochastically based natural language understanding component across tasks and languages. Stochastically based methods have been applied in the BBN HUM [5] the AT T CHRONUS [7] systems and at LIMSI CNRS [1] for the American ARPA ATIS (Air Travel Information Services) task 1 . Since the stochasticallybased decoding techniques are rather similar across the sites, the systems differ primarily in the definition of the knowledge sources, which are represented in the form of semantic labels. In a ....
....Kiosk) A spoken language system in French has been developed at LIMSI [3] for this task, which allows users to obtain train travel information including schedules, services and fares. We investigate language and domain portability by porting the stochastically based semantic analyzer presented in [1] from the American ATIS task to the French MASK application. For the American ATIS task, a rule based version [2, 4] was used to automatically producea corpus of semantic representations for training the stochastically based component in [1] enabling a direct comparison between both methods. In ....
[Article contains additional citation context not shown here]
W. Minker, S. Bennacef, and J. L. Gauvain. A Stochastic Case Frame Approach for Natural Language Understanding. Proc. ICSLP-96.
Stochastic Speech Understanding for Human-Computer Dialogue - Bohus, Boldea (Correct)
No context found.
W. Minker, S. Bennacef, and J.L. Gauvin. A Stochastic Case Frame Approach for Natural Language Understanding. In Proceedings 4th International Conference on Spoken Language Processing, pages 1013-16, Philadelphia, 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC