The BBN/HARC spoken language understanding system

Bates, Madeleine; Bobrow, Robert; Fung, Pascale; Ingria, Robert; Kubala, Francis; Makhoul, John; Nguyen, Long; Schwartz, Richard; Stallard, David

doi:10.1109/icassp.1993.319244

Cited by 21 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For that, each hypothesis gets a weight derived from its a posteriori likelihood such that the weights add up to one. The definition of the weights was inspired by the list-based confidence measure discussed in Section VI-A and is given in (3). Every sentence now contributes to the adaptation material according to its weight.…”

Section: Online Adaptation Of Language Modelsmentioning

confidence: 99%

“…Of course, systems with comparable functionality and complexity have been developed by several groups. Prominent examples are the air travel information systems by MIT (Pegasus [39]), CMU [15], BBN [3], and SRI [7], the train information system RailTel [23], the multimedia service kiosk Mask [24]) by LIMSI, the weather information system Jupiter by MIT [38], the How May I Help You? call routing system [14] by AT&T, and the large-scale directory assistance systems by CSELT [5], and AT&T (VPQ [8]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The thoughtful elephant: strategies for spoken dialog systems

Souvignier

Kellner

Rueber

et al. 2000

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

In this paper we present technology used in spoken dialog systems for applications of a wide range. They include tasks from the travel domain and automatic switchboards as well as large scale directory assistance. The overall goal in developing spoken dialog systems is to allow for a natural and flexible dialog flow similar to human-human interaction. This imposes the challenging task to recognize and interpret user input, where he/she is allowed to choose from an unrestricted vocabulary and an infinite set of possible formulations. We therefore put emphasis on strategies that make the system more robust while still maintaining a high level of naturalness and flexibility. In view of this paradigm, we found that two fundamental principles characterize many of the proposed methods: 1) to consider available sources of information as early as possible, and 2) to keep alternative hypotheses and delay the decision for a single option as long as possible.We describe how our system architecture caters to incorporating application specific knowledge, including, for example, database constraints, in the determination of the best sentence hypothesis for a user turn. On the next higher level, we use the dialog history to assess the plausibility of a sentence hypothesis by applying consistency checks with information items from previous user turns. In particular, we demonstrate how combination decisions over several turns can be exploited to boost the recognition performance of the system. The dialog manager can also use information on the dialog flow to dynamically modify and tune the system for the specific dialog situations. An important means to increase the "intelligence" of a spoken dialog system is to use confidence measures. We propose methods to obtain confidence measures for semantic items, whole sentences and even full N-best lists and give examples for the benefits obtained from their application. Experiences from field tests with our systems are summarized that have been found crucial for the system acceptance.Index Terms-Application specific knowledge, combined decisions, confidence measures, dialog history, natural language understanding, spoken dialog systems.

show abstract

Section: Online Adaptation Of Language Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The thoughtful elephant: strategies for spoken dialog systems

Souvignier

Kellner

Rueber

et al. 2000

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

show abstract

“…In spoken language applications, Delphi is interfaced to the output of the Byblos speech recognition system (Bates et al, 1993). The N-best paradigm is used, in which the recognizer outputs in order its top N guesses at the transcription of the sentence, for some value of N (usually 5).…”

Section: Interface To a Speech Recognizermentioning

confidence: 99%

The Delphi natural language understanding system

Bates¹,

Bobrow²,

Ingria³

et al. 1994

Proceedings of the Fourth Conference on Applied Natural Language Processing -

View full text Add to dashboard Cite

This paper presents Delphi, the natural language component of the BBN Spoken Language System. Delphi is a domainindependent natural language question answering system that is solidly based on linguistic principles, yet which is also robust to ungrammatical input. It includes a domain-independent, broad-coverage grammar of English. Analysis components include an agenda-based best-first parser and a fallback component for partial understanding that works by fragment combination. Delphi has been formally evaluated in the ARPA Spoken Language program's ATIS (Airline Travel Information System) domain, and has performed well. Delphi has also been ported to a spoken language demonstration system in an Air Force Resource Management domain. We discuss results of the evaluation as well as the porting process.

show abstract

“…In the initial system, the BBN BYBLOS Continuous Speech Recognition system [4,5,6] (see Figure I) was used without modification on an on-line cursive handwriting corpus created from prompts from the ARPA Airline Travel Information Service (ATIS) corpus [7]. These full sentence prompts (approximately 10 words per sentence) were written by a single subject.…”

Section: Airline Travel Information Service: An Initial 3050 Word 52 Symbol Taskmentioning

confidence: 99%

On-line cursive handwriting recognition using hidden Markov models and statistical grammars

Makhoul¹,

Starner²,

Schwartz³

et al. 1994

Proceedings of the Workshop on Human Language Technology - HLT '94

View full text Add to dashboard Cite

The BYBLOS continuous speech recognition system is applied to on-line cursive handwriting recognition. By exploiting similarities between on-line cursive handwriting and continuous speech recognition, we can use the same base system adapted to handwriting feature vectors instead of speech. The use of hidden Markov models obviates the need for segmentation of the handwritten script sentences before recognition. To test our system, we collected handwritten sentences using text from the ARPA Airline Travel Information Service (ATIS) and the ARPA Wall Street Journal (WSJ) corpora. In an initial experiment on the ATIS data, a word error rate of 1.1% was achieved with a 3050-word lexicon, 52-character set, collected from one writer. In a subsequent writer-dependent test on the WSJ data, error rates ranging between 2%-5% were obtained with a 25,595word lexicon, 86-character set, collected from six different writers. Details of the recognition system, the data collection process, and analysis of the experiments are presented.

show abstract

The BBN/HARC spoken language understanding system

Cited by 21 publications

References 10 publications

The thoughtful elephant: strategies for spoken dialog systems

The thoughtful elephant: strategies for spoken dialog systems

The Delphi natural language understanding system

On-line cursive handwriting recognition using hidden Markov models and statistical grammars

Contact Info

Product

Resources

About