Progress report on the Chronus system

Pieraccini, Roberto; Tzoukermann, Evelyne; Gorelov, Zakhar; Levin, Esther; Lee, Chin‐Hui; Gauvain, Jean‐Luc

doi:10.3115/1075527.1075543

Cited by 12 publications

(7 citation statements)

References 11 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the "Departure Date" slot expressed as the word "tomorrow" has to be normalized to something like "03/11/2013" in order to be useful for searching a flight database. Most ATIS systems employed either a statistical classification approach (those coming from the speech processing community) such as AT&T's CHRONUS [37] and BBN's hidden understanding models [30] or a knowledge-based approach (mostly from the computational linguistics community) such as the MIT's TINA [42], CMU's Phoenix [50], and SRI's Gemini [17].…”

Section: Brief Historymentioning

confidence: 99%

Natural Language Understanding and Prediction: from Formal Grammars to Large Scale Machine Learning

Duta

2014

Fundamenta Informaticae

View full text Add to dashboard Cite

Scientists have long dreamed of creating machines humans could interact with by voice. Although one no longer believes Turing's prophecy that machines will be able to converse like humans in the near future, real progress has been made in the voice and text-based human-machine interaction. This paper is a light introduction and survey of some deployed natural language systems and technologies and their historical evolution. We review two fundamental problems involving natural language: the language prediction problem and the language understanding problem. While describing in detail all these technologies is beyond our scope, we do comment on some aspects less discussed in the literature such as language prediction using huge models and semantic labeling using Marcus contextual grammars.

show abstract

Section: Brief Historymentioning

confidence: 99%

Natural Language Understanding and Prediction: from Formal Grammars to Large Scale Machine Learning

Duta

2014

Fundamenta Informaticae

View full text Add to dashboard Cite

show abstract

“…An early example of a purely statistical approach to semantic parsing is the finite state semantic tagger used in AT&T's CHRONUS system [10]. In this system, utterance generation is modeled by an HMM-like process in which the hidden states correspond to semantic concepts and the state outputs correspond to the individual words.…”

Section: S S P R O T E I N a C T I V A T Ementioning

confidence: 99%

Discriminative Training of the Hidden Vector State Model for Semantic Parsing

Zhou

2009

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

In this paper, we discuss how discriminative training can be applied to the Hidden Vector State (HVS) model in different task domains. The HVS model is a discrete Hidden Markov Model (HMM) in which each HMM state represents the state of a push-down automaton with a finite stack size. In previous applications, Maximum Likelihood estimation (MLE) is used to derive the parameters of the HVS model. However, MLE makes a number of assumptions and unfortunately some of these assumptions do not hold. Discriminative training, without making such assumptions, can improve the performance of the HVS model by discriminating the correct hypothesis from the competing hypotheses. Experiments have been conducted in two domains: the travel domain for the semantic parsing task using the DARPA Communicator data and the ATIS data, and the bioinformatics domain for the information extraction task using the GENIA corpus. The results demonstrate modest improvements of the performance of the HVS model using discriminative training. In the travel domain, discriminative training of the HVS model gives a relative error reduction rate of 31% in F-measure when compared with MLE on the DARPA Communicator data and 9% on the ATIS data. In the bioinformatics domain, a relative error reduction rate of 4% in F-measure is achieved on the GENIA corpus.

show abstract

“…The rejection heuristic is based on the measure of success in the operation of template generation (how many decoded concepts are successfully matched to a value), although more sophisticated heuristics can be developed. The results [24] on the complete test set, from text input, account for 68% of correct answers, 18% wrong answers and 14% rejects. When the system was coupled with a speech recognizer through the best first hypothesis, the performance dropped to 52% of correct answers, 26% wrong answers and 22% rejects.…”

Section: Experimental Performancementioning

confidence: 99%

“…I, XXIV, XCIX) and their correspondent decimal representation (e.g. 1,24,99). Fortunately, in a natural language understanding task, we may have the freedom of choosing the semantic representation, like we did in the implementation of CHRONUS explained above.…”

Section: The Sequential Correspondence Assumptionmentioning

confidence: 99%

A Learning Approach to Natural Language Understanding

Pieraecini

Levin

1995

Speech Recognition and Coding

Self Cite

View full text Add to dashboard Cite

In this paper we propose a learning paradigm for the problem of understanding spoken language. The basis of the work is in a formalization of the understanding problem as a communication problem. This results in the definition of a stochastic model of the production of speech or text starting from the meaning of a sentence. The resulting understanding algorithm consists in a Viterbi maximization procedure, analogous to that commonly used for recognizing speech. The algorithm was implemented for building a module, called conceptual decoder for the decoding of the conceptual content of sentences in an airline information domain. The decoding module is the basis on which a complete prototypical understanding system was implemented and whose performance are discussed in the paper. The problems, the possible solutions and the future directions of the learning approach to language understanding are also discussed in this paper.

show abstract

Progress report on the Chronus system

Cited by 12 publications

References 11 publications

Natural Language Understanding and Prediction: from Formal Grammars to Large Scale Machine Learning

Natural Language Understanding and Prediction: from Formal Grammars to Large Scale Machine Learning

Discriminative Training of the Hidden Vector State Model for Semantic Parsing

A Learning Approach to Natural Language Understanding

Contact Info

Product

Resources

About