S. Issar and W. Ward, "CMU's Robust Spoken Language Understanding System," in Eurospeech'93, 1993, pp. 2147--2150.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....request requires an appropriate formalism to represent the meaning of an utterance. For a specific application, one must always try to find a compromise between accuracy and the complexity of the implementation [8] Different semantic representations have been proposed. Among them, case frames [9], semantic frames [10] semantic graphs [11] and variants of tree based concepts [3] as well as flat concepts [4] are the most prominent. Since we regard NLU as a special case of a translation problem, we have chosen a flat concept based target language as meaning representation. The remainder ....

S. Issar and W. Ward, "CMU's Robust Spoken Language Understanding System," in EuroSpeech'93, vol. 3, pp. 2147--2149, September 1993.

....processing is to extract meaningful information: in this, the task is understanding rather than transcription. For extracting meaning from spontaneous speech full coverage grammars tend to be too brittle. In the 1992 DARPA ATIS task competition, CMU s Phoenix parser was the best scoring system (Issar and Ward, 1993). Phoenix operates in a loosely coupled architecture on the 1 best transcript produced by the recognizer. Conceptually it is a semantic case frame parser (Hayes et al. 1986) As such, it allows slots within a particular case frame to be filled in any order, and allows out of grammar words between ....

S. Issar and W. Ward. 1993. Cmu's robust spoken language understanding system. In Eurospeech '93, pages 2147--2150.

....due to ungrammatical syntactic constructs may be reduced, if those portions containing important semantic information could be identified whilst ignoring the non essential or redundant parts. The robust parsing in CMU s PHOENIX system follows this strategy and applies a case grammar formalism [4]. L ATIS, a spoken language understanding system for a French version of the ARPA ATIS task has been previously described [2] Its spoken language understanding component is also based on a case grammar formalism [3] which detects domain related concepts and instanciates the corresponding semantic ....

S. Issar and W. Ward. CMU's Robust Spoken LanguageUnderstanding System. In Proceedings of the European Conference on Speech Technology, EUROSPEECH, September 1993.

....speech recognition errors. On the other hand, the good thing is that spoken language tend to contain less complex structures than written language. Several methods have been suggested compensate for these speech related problems: e.g. score and penalties, probabilistic rules, and skipping words [5, 15, 11, 8]. A small community have experimented with either purely statistical approaches[2, 14] or connectionist based approaches [1, 12, 9, 16] Their main advantages are learnability and robustness. All connectionist approaches to our knowledge, have suffered from one or more of the following problems: ....

Sunil Issar and Wayne Ward. CMU's robust spoken language understanding system. In Proceedings of Eurospeech, 1993.

....provide the best parse or the N best parses. Therefore, a mixture of hard and soft rules (scores and penalties, probabilistic rules, and constraints) is applied. In most parsers, the core consists of hand modeled rules. With great success, these rules have been annotated with soft information[3, 10, 8, 6]. In this paper, we present a parser, FeasPar, that learns to parse, instead of having hand modeled rules. The FeasPar architecture consists of neural networks and a search. The search finds the best feature structure based on the neural network outputs, and feature structure constraints. FeasPar ....

Sunil Issar and Wayne Ward, `CMU's robust spoken language understanding system', in Proceedings of Eurospeech, (1993).

....(for example, the first three letters of the departure city) A spoken language interface can provide a more natural communication approach in these applications. Our goal is to allow the users to communicate in a natural way, because it reduces the amount of learning by the user. The CMU ATIS [9, 3] system and other similar systems [1] demonstrate the feasibility of using spoken natural language queries for a database retrieval task. However, we still need to address several issues before we can build robust spoken language applications. For example, we need to generate a language model that ....

....issues before we can build robust spoken language applications. For example, we need to generate a language model that can be used by the recognizer to reduce the search space. Finite state language models may work for simple speech enabled menu commands. However, they may not be the best choice [3] for database retrieval tasks where the user can ask a large number of questions. We are conductingexperiments [11] with a recognizer that uses both stochastic and finite state language models. In this paper, we will look at the issues that arise in generating stochastic languagemodels for a new ....

[Article contains additional citation context not shown here]

Sunil Issar and Wayne Ward. CMU's robust spoken language understanding system. In Proceedings of Eurospeech, pages 2147--2150, September 1993.

....Historically, spoken language understanding research developed from the speech recognition (SR) tradition with its emphasis on identifying words and phrases. Current systems have largely evolved through a series of heuristicsdriven enhancements to existing speech recognizers (e.g. 3] [4], 9] This evolution has led to what we term the SR bias, an emphasis on getting the words right as the measurable goal of a spoken language component; system enhancements are viewed as improving the performance of the recognizer. We believe that this SR centered approach does not offer a ....

Issar, S. & Ward, W. (1993). "CMU's Robust Spoken Language Understanding System," Eurospeech `93, pp. 2147-2150.

No context found.

S. Issar and W. Ward, "CMU's Robust Spoken Language Understanding System," in Eurospeech'93, 1993, pp. 2147--2150.

No context found.

S. Issar, W. Ward, "CMU's robust spoken language understanding system, " in Proc. EuroSpeech'93, Berlin, Germany, pp. 2147--2150.

No context found.

S. Issar and W. Ward. 1993. "CMU's Robust Spoken Language Understanding System. In Eurospeech '93, pages 2147--2150.

No context found.

Sunil Issar and Wayne Ward. CMU's robust spoken language understanding system. In Proceedings of Eurospeech, 1993.

No context found.

Sunil Issar and Wayne Ward. 1993. CMU's robust spoken language understanding system. In Proceedings of Eurospeech.

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