Dialogue act recognition using maximum entropy

Kwok Cheung Lan, Kei Shiu Ho, Robert Wing Pong Luk and and Hong Va Leong

Journal of the American Society for Information Science and Technology, 2008, vol. 59, issue 6, 859-874

Abstract: A dialogue‐based interface for information systems is considered a potentially very useful approach to information access. A key step in computer processing of natural‐language dialogues is dialogue‐act (DA) recognition. In this paper, we apply a feature‐based classification approach for DA recognition, by using the maximum entropy (ME) method to build a classifier for labeling utterances with DA tags. The ME method has the advantage that a large number of heterogeneous features can be flexibly combined in one classifier, which can facilitate feature selection. A unique characteristic of our approach is that it does not need to model the prior probability of DAs directly, and thus avoids the use of a discourse grammar. This simplifies the implementation of the classifier and improves the efficiency of DA recognition, without sacrificing the classification accuracy. We evaluate the classifier using a large data set based on the Switchboard corpus. Encouraging performance is observed; the highest classification accuracy achieved is 75.03%. We also propose a heuristic to address the problem of sparseness of the data set. This problem has resulted in poor classification accuracies of some DA types that have very low occurrence frequencies in the data set. Preliminary evaluation shows that the method is effective in improving the macroaverage classification accuracy of the ME classifier.

Date: 2008
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1002/asi.20777

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bla:jamist:v:59:y:2008:i:6:p:859-874

Ordering information: This journal article can be ordered from
https://doi.org/10.1002/(ISSN)1532-2890

Access Statistics for this article

More articles in Journal of the American Society for Information Science and Technology from Association for Information Science & Technology
Bibliographic data for series maintained by Wiley Content Delivery ().