Dialogue act recognition with Bayesian networks for Dutch dialogues

Keizer, Simon; Akker, Rieks op den; Nijholt, Anton

doi:10.3115/1118121.1118134

Cited by 50 publications

(48 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those methods include n-gram language models, hidden Markov models, nave Bayes classifiers, Bayesian networks, multilayer perceptrons, decision trees, transformation-based learning, and memory-based learning [3,5,9,[20][21][22][23][24][25]. Most of them, however, utilized language model information, which cannot be used in our problem since the two types, DQs and statements, have the same transcription.…”

Section: Introductionmentioning

confidence: 99%

Automatic recognition of Indonesian declarative questions and statements using polynomial coefficients of the pitch contours

Effendy

Sairyo

Furui

et al. 2009

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

Abstract:We propose an automatic utterance type recognizer that distinguishes declarative questions from statements in Indonesian speech. Since utterances in these two types have the same words with the same order and differ only in their intonations, their classification requires not only a speech recognizer, but also an intonation recognizer. In this paper, the most important utterance part for distinguishing those two types is first identified by perceptual experiments. Then, an utterance type recognizer using that part is proposed, where polynomial expansion is used as a feature extractor and a neural network is used as a classifier. We evaluated our method using Indonesian speech database including 29 pairs of sentences of those two types, each of which uttered by 35 speakers. It was proved that final word and final-two-syllables are equally effective for the discrimination of each utterance. The proposed recognizer achieved the best accuracy of 89.1% when the order of polynomial expansion was three and the neural network was a linear perceptron.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic recognition of Indonesian declarative questions and statements using polynomial coefficients of the pitch contours

Effendy

Sairyo

Furui

et al. 2009

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

show abstract

“…These include Hidden Markov Models [11], Bayesian Networks [32], Discriminative Dynamic Bayesian Networks [33], BayesNet [28], Memory-based [34] and Transformation-based Learning [35], Decision Trees [36], Neural Networks [37], but also more advanced approaches such as Boosting [38], Latent Semantic Analysis [39], Hidden Backoff Models [40], Maximum Entropy Models [41], Conditional Random Fields [31,30] and Triangular-chain CRF [42].…”

Section: Related Workmentioning

confidence: 99%

“…Words Inflected Form The word form is used as a baseline lexical feature in most modern lexicalized natural language processing approaches [11,44,32,33]. In our case, sentence segmentation is known but capitalization of the first word of the sentence is removed, which decreases the total number of features in our model without impacting accuracy, thanks to the insertion of a special "start-of-utterance" word.…”

Section: Baseline Featuresmentioning

confidence: 99%

Automatic dialogue act recognition with syntactic features

Král

Cerisara

2014

Lang Resources & Evaluation

View full text Add to dashboard Cite

This work studies the usefulness of syntactic information in the context of automatic dialogue act recognition in Czech. Several pieces of evidence are presented in this work that support our claim that syntax might bring valuable information for dialogue act recognition. In particular, a parallel is drawn with the related domain of automatic punctuation generation and a set of syntactic features derived from a deep parse tree is further proposed and successfully used in a Czech dialogue act recognition system based on Conditional Random Fields. We finally discuss the possible reasons why so few works have exploited this type of information before and propose future research directions to further progress in this area.

show abstract

“…Previous and possibly future dialogue acts are events that need to be "appraised". In earlier research (Keizer et al 2002) we used Bayesian networks in order to predict dialogue acts. While this approach is unconvential from the usual point of view of event appraisal, it is an accepted approach in dialogue modeling research that has been implemented in a number of dialogue systems.…”

Section: Future Research Approachesmentioning

confidence: 99%