---
title: "Dialogue Act Recognition with Bayesian — Keizer 2002"
description: "The authors address dialogue act recognition (DAR) for Dutch-language agents in the Virtual Music Centre (VMC)."
authors: ["Simon Keizer", "Rieks op den Akker", "Anton Nijholt"]
year: 2002
venue: "Proceedings of the Third SIGdial Workshop on Discourse and Dialogue"
source: "https://aclanthology.org/W02-0213/"
doi: "10.3115/1118121.1118134"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/keizer-2002-dialogue-act-recognition-bayesian-networks/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/keizer-2002-dialogue-act-recognition-bayesian-networks/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2002](https://md.research.elamur.ai/free/papers/2002/) / Dialogue Act Recognition with Bayesian Networks for Dutch Dialogues

# Dialogue Act Recognition with Bayesian Networks for Dutch Dialogues

**Authors:** [Simon Keizer](https://md.research.elamur.ai/free/authors/simon-keizer/), Rieks op den Akker, Anton Nijholt · **Year:** 2002 · **Venue:** Proceedings of the Third SIGdial Workshop on Discourse and Dialogue · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/W02-0213/) · [PDF](https://aclanthology.org/W02-0213.pdf) · [DOI 10.3115/1118121.1118134](https://doi.org/10.3115/1118121.1118134) · [OpenAlex](https://openalex.org/W2155939513)

**Citations:** 68 citations (openalex-snapshot · 2026-10-14) · [15](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The authors address dialogue act recognition (DAR) for Dutch-language agents in the Virtual Music Centre (VMC). This environment hosts Karin, an embodied agent that gives theatre information, and a separate navigation assistant. They treat DAR as probabilistic inference: given features of the user's utterance and the dialogue context, the system chooses the most probable dialogue act. A Bayesian network supplies the model.

Two experimental settings share the DAMSL-based annotation scheme, using both its forward-looking and backward-looking layers.
- **SCHISMA corpus:** The network structure was designed manually, and its conditional probabilities were trained on annotated data.
- **Navigation corpus:** This small corpus was grown iteratively. Both the structure (via the K2 algorithm) and the probabilities (via MAP) were learned automatically.

On the navigation data, accuracy improved after one enlargement cycle. The Bayesian network also beat a decision tree and Naive Bayes trained on the same data. The authors acknowledge that the data are still scarce. Even so, the work is an early demonstration that Bayesian networks can be learned from annotated corpora for DAR. Unlike single-target classifiers, they also give posterior probabilities for every variable in the network.

## Key points
- **SCHISMA corpus:** 64 typed Wizard of Oz dialogues about theatre performances and ticket booking. Twenty of them were hand-annotated with DAMSL acts, extended with ref-question, if-question and alts-question.
- **Navigation features:** Surface cues such as startsWithCanYou, startsWithIWant, containsOkay and containsLocativePrep, plus utterance length. The previous system dialogue act serves as the context feature.
- **Navigation results, first cycle:** The initial corpus had 81 utterances, split 75% for training and 25% for testing. Accuracy was 57.1% for forward-looking functions and 81.0% for backward-looking functions.
- **Navigation results, after enlargement:** Interactively collected data raised accuracy to 76.5% (forward-looking) and 88.2% (backward-looking).
- **Baseline comparison on the same data:** A decision tree reached 50.0% and 64.7%, and Naive Bayes reached 55.9% and 61.8%. Both were clearly outperformed by the Bayesian network.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

Topics: [Speech act theory](https://md.research.elamur.ai/free/topics/speech-act-theory/)

## Cited by

Cited by

15 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 14 not yet.

- [Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions](https://md.research.elamur.ai/free/papers/li-2020-modeling-local-contexts-joint-dialogue/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{keizer2002dialogue,
  title = {{Dialogue Act Recognition with Bayesian Networks for Dutch Dialogues}},
  author = {Keizer, Simon and Akker, Rieks op den and Nijholt, Anton},
  booktitle = {Proceedings of the Third SIGdial Workshop on Discourse and Dialogue},
  year = {2002},
  doi = {10.3115/1118121.1118134},
  url = {https://doi.org/10.3115/1118121.1118134}
}
```

- [← previous Combining Unsupervised and Supervised Methods for PP Attachment Disambiguation](https://md.research.elamur.ai/free/papers/aclbulk-2002-volk-combining-unsupervised-supervised-methods-pp/)
- [next → Discriminative Training and Maximum Entropy Models for Statistical Machine Translation](https://md.research.elamur.ai/free/papers/och-2002-discriminative-training-maximum-entropy-models/)
- [↑ back to papers of 2002](https://md.research.elamur.ai/free/papers/2002/)

## References

14 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. J. Allen and M. Core. 1997. Draft of DAMSL: Dialog Act Markup in Several Layers. URL: [http://www.cs.rochester.edu/research/trains/annotation](http://www.cs.rochester.edu/research/trains/annotation). [↗](http://www.cs.rochester.edu/research/trains/annotation)
2. T. Andernach. 1996. A machine learning approach to the classification and prediction of dialogue utterances. In Proceedings of the Second International Conference on New Methods in Language Processing (NeMLaP-2), pages 98–109, Ankara, Turkey. [find](https://scholar.google.com/scholar?q=T%2E+Andernach%2E+1996%2E+A+machine+learning+approach+to+the+classification+and+prediction+of+dialogue+utterances%2E+In+Proceedings+of+the+Second+International+Conference+on+New+Methods+in+Language+Processing)
3. G. F. Cooper and E. Herskovits. 1992. A Bayesian method for the induction of probabilistic networks from data. Machine Learning, 9:309–347. [↗](https://doi.org/10.1007/bf00994110)
4. D. Heckerman. 1999. A tutorial on learning with Bayesian networks. In M. Jordan, editor, Learning in Graphical Models. MIT Press, Cambridge MA. [↗](https://doi.org/10.1007/978-94-011-5014-9_11)
5. S. Keizer. 2001. A Bayesian approach to dialogue act classification. In P. Kühnlein, H. Rieser, and H. Zeevat, editors, BI-DIALOG 2001: Proc. of the 5th Workshop on Formal Semantics and Pragmatics of Dialogue, pages 210–218. [find](https://scholar.google.com/scholar?q=S%2E+Keizer%2E+2001%2E+A+Bayesian+approach+to+dialogue+act+classification%2E+In+P%2E+Ku%CC%88hnlein%2C+H%2E+Rieser%2C+and+H%2E+Zeevat%2C+editors%2C+BI%2DDIALOG+2001%3A+Proc%2E+of+the+5th+Workshop+on+Formal+Semantics+and+Pragmatics+of)
6. J. van Luin, R. op den Akker, and A. Nijholt. 2001. A dialogue agent for navigation support in virtual reality. In J. Jacko and A. Sears, editors, ACM SIGCHI Conf. CHI 2001: Anyone. Anywhere, pages 117–118, Seattle. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=J%2E+van+Luin%2C+R%2E+op+den+Akker%2C+and+A%2E+Nijholt%2E+2001%2E+A+dialogue+agent+for+navigation+support+in+virtual+reality%2E+In+J%2E+Jacko+and+A%2E+Sears%2C+editors%2C+ACM+SIGCHI+Conf%2E+CHI+2001%3A+Anyone%2E+Anywhere%2C+pages+11)
7. T.M. Mitchell. 1997. Machine Learning. Computer Science Series. McGraw-Hill. [find](https://scholar.google.com/scholar?q=T%2EM%2E+Mitchell%2E+1997%2E+Machine+Learning%2E+Computer+Science+Series%2E+McGraw%2DHill%2E)
8. A. Nijholt, J. Zwiers, and B. van Dijk. 2001. Maps, agents and dialogue for exploring a virtual world. In N. Callaos, S. Long, and M. Loutfi, editors, 5th World Multiconference on Systemics, Cybernetics and Informatics (SCI 2001), volume VII of Human Information and Education Systems, pages 94–99, Orlando, July. [find](https://scholar.google.com/scholar?q=A%2E+Nijholt%2C+J%2E+Zwiers%2C+and+B%2E+van+Dijk%2E+2001%2E+Maps%2C+agents+and+dialogue+for+exploring+a+virtual+world%2E+In+N%2E+Callaos%2C+S%2E+Long%2C+and+M%2E+Loutfi%2C+editors%2C+5th+World+Multiconference+on+Systemics%2C+Cyberneti)
9. A. Nijholt. 2000. Multimodal interactions with agents in virtual worlds. In N. Kasabov, editor, Future Directions for Intelligent Systems and Information Science, Physica-Verlag: Studies in Fuzziness and Soft Computing, chapter 8, pages 148– 173. Springer. [↗](https://doi.org/10.1007/978-3-7908-1856-7_8)
10. T. Paek and E. Horvitz. 2000. Conversation as action under uncertainty. In 16th Conference on Uncertainty in Artificial Intelligence (UAI-2000), pages 455–464, San Francisco, CA, June. Morgan Kaufmann Publishers. [find](https://scholar.google.com/scholar?q=T%2E+Paek+and+E%2E+Horvitz%2E+2000%2E+Conversation+as+action+under+uncertainty%2E+In+16th+Conference+on+Uncertainty+in+Artificial+Intelligence+%28UAI%2D2000%29%2C+pages+455%E2%80%93464%2C+San+Francisco%2C+CA%2C+June%2E+Morgan+Kaufmann)
11. J. Pearl. 1988. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann. [find](https://scholar.google.com/scholar?q=J%2E+Pearl%2E+1988%2E+Probabilistic+Reasoning+in+Intelligent+Systems%3A+Networks+of+Plausible+Inference%2E+Morgan+Kaufmann%2E)
12. S.G. Pulman. 1996. Conversational games, belief revision and Bayesian networks. In J. Landsbergen, J. Odijk, K. van Deemter, and G. Veldhuijzen van Zanten, editors, Computational Linguistics in the Netherlands. [find](https://scholar.google.com/scholar?q=S%2EG%2E+Pulman%2E+1996%2E+Conversational+games%2C+belief+revision+and+Bayesian+networks%2E+In+J%2E+Landsbergen%2C+J%2E+Odijk%2C+K%2E+van+Deemter%2C+and+G%2E+Veldhuijzen+van+Zanten%2C+editors%2C+Computational+Linguistics+in+the+Ne)
13. A. Stolcke et al. 2000. Dialogue act modelling for automatic tagging and recognition of conversational speech. Computational Linguistics, 26(3):339– 374. [find](https://scholar.google.com/scholar?q=A%2E+Stolcke+et+al%2E+2000%2E+Dialogue+act+modelling+for+automatic+tagging+and+recognition+of+conversational+speech%2E+Computational+Linguistics%2C+26%283%29%3A339%E2%80%93+374%2E)
14. D.R. Traum. 2000. 20 questions on dialogue act taxonomies. Journal of Semantics, 17(1):7–30. [↗](https://doi.org/10.1093/jos/17.1.7)