Discriminative estimation of interpolation parameters for language model classifiers

Warnke, Volker; Harbeck, Stefan; Nöth, Elmar; Niemann, Heinrich; Levit, Michael

doi:10.1109/icassp.1999.758178

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We performed experiments to determine the effect of the availability of the correct segmentation of dialogue turns in utterances in the statistical DA labelling framework. Our results reveal that, as shown in previous work (Warnke et al, 1999), having the correct segmentation is very important in obtaining accurate results in the labelling task. This conclusion is supported by the results obtained in very different dialogue corpora: different amounts of training and test data, different natures (general and taskoriented), different sets of labels, etc.…”

Section: Discussionsupporting

confidence: 84%

Segmented and unsegmented dialogue-act annotation with statistical dialogue models

Martínez-Hinarejos

Granell

Benedí

2006

Proceedings of the COLING/ACL on Main Conference Poster Sessions -

View full text Add to dashboard Cite

Dialogue systems are one of the most challenging applications of Natural Language Processing. In recent years, some statistical dialogue models have been proposed to cope with the dialogue problem. The evaluation of these models is usually performed by using them as annotation models. Many of the works on annotation use information such as the complete sequence of dialogue turns or the correct segmentation of the dialogue. This information is not usually available for dialogue systems. In this work, we propose a statistical model that uses only the information that is usually available and performs the segmentation and annotation at the same time. The results of this model reveal the great influence that the availability of a correct segmentation has in obtaining an accurate annotation of the dialogues.

show abstract

Section: Discussionsupporting

confidence: 84%

Segmented and unsegmented dialogue-act annotation with statistical dialogue models

Martínez-Hinarejos

Granell

Benedí

2006

Proceedings of the COLING/ACL on Main Conference Poster Sessions -

View full text Add to dashboard Cite

show abstract

“…The standard n-gram models for DA discrimination with lexical cues are probably suboptimal for this task, simply because they are trained in the maximum likelihood framework, without explicitly optimizing discrimination between DA types. This may be overcome by using discriminative training procedures (Warnke et al 1999;Ohler, Harbeck, and Niemann 1999). Training neural networks directly with posterior probability (Ries 1999a) seems to be a more principled approach and it also offers much easier integration with other knowledge sources.…”

Section: Discussion and Issues For Future Researchmentioning

confidence: 99%

“…Finally, Ries (1999a) shows that neural networks using only unigram features can be superior to higher-order n-gram DA models. Warnke et al (1999) and Ohler, Harbeck, and Niemann (1999) use related discriminative training algorithms for language models. Woszczyna and Waibel (1994) and Suhm and Waibel (1994), followed by Chu-Carroll (1998), seem to have been the first to note that such a combination of word and dialogue n-grams could be viewed as a dialogue HMM with word strings as the observations.…”

Section: Tag Examplementioning

confidence: 99%

Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech

Stolcke

Coccaro

Bates

et al. 2000

Computational Linguistics

817

756

View full text Add to dashboard Cite

We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as STATEMENT, QUESTION, BACKCHANNEL, AGREEMENT, DIS-AGREEMENT, and APOLOGY. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue acts are modeled via a dialogue act n-gram. The statistical dialogue grammar is combined with word n-grams, decision trees, and neural networks modeling the idiosyncratic lexical and prosodic manifestations of each dialogue act. We develop a probabilistic integration of speech recognition with dialogue modeling, to improve both speech recognition and dialogue act classification accuracy. Models are trained and evaluated using a large hand-labeled database of 1,155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We achieved good dialogue act labeling accuracy (65% based on errorful, automatically recognized words and prosody, and 71% based on word transcripts, compared to a chance baseline accuracy of 35% and human accuracy of 84%) and a small reduction in word recognition error.

show abstract

Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition

Chou¹

2000

Proc. IEEE

View full text Add to dashboard Cite

Discriminative estimation of interpolation parameters for language model classifiers

Cited by 4 publications

References 8 publications

Segmented and unsegmented dialogue-act annotation with statistical dialogue models

Segmented and unsegmented dialogue-act annotation with statistical dialogue models

Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech

Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition

Contact Info

Product

Resources

About