---
title: "Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training (2018)"
description: "The paper addresses dialogue act (DA) classification: assigning each utterance in a conversation a label such as… 48 references, cited by 6 papers here."
authors: ["Yao Wan", "Wenqiang Yan", "Jianwei Gao", "Zhou Zhao", "Jian Wu", "Philip S. Yu"]
year: 2018
venue: "arXiv:1811.05021"
source: "https://arxiv.org/abs/1811.05021"
doi: "10.48550/arxiv.1811.05021"
arxiv: "1811.05021"
licence: "arXiv non-exclusive distribution licence (read only, no redistribution)"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wan-2018-improved-dynamic-memory-network-dialogue/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wan-2018-improved-dynamic-memory-network-dialogue/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/5/) / Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training

# Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training

**Authors:** Yao Wan, Wenqiang Yan, Jianwei Gao, [Zhou Zhao](https://md.research.elamur.ai/free/en/authors/zhou-zhao/), [Jian Wu](https://md.research.elamur.ai/free/en/authors/jian-wu/) and [Philip S. Yu](https://md.research.elamur.ai/free/en/authors/philip-s-yu/) · **Year:** 2018 · **Venue:** [arXiv:1811.05021](https://md.research.elamur.ai/free/en/venues/ieee-international-conference-on-big-data-bigdata/) ([BigData 2018](https://md.research.elamur.ai/free/en/venues/ieee-international-conference-on-big-data-bigdata/2018/)) · **Licence:** [arXiv non-exclusive distribution licence (read only, no redistribution)](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1811.05021) · [PDF](https://arxiv.org/pdf/1811.05021) · [DOI 10.48550/arxiv.1811.05021](https://doi.org/10.48550/arxiv.1811.05021) · [arXiv 1811.05021](https://arxiv.org/abs/1811.05021) · [OpenAlex](https://openalex.org/W2901101385)

**Citations:** 8 citations (OpenAlex, 2026-10-14) · [6](https://md.research.elamur.ai/free/en/papers/wan-2018-improved-dynamic-memory-network-dialogue/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper addresses dialogue act (DA) classification: assigning each utterance in a conversation a label such as Question, Answer, Greeting or Backchannel that captures what the speaker intends. The authors identify two weaknesses in earlier systems. They rely either on hand-built features or on models with limited memory of prior turns, and they are fragile under small adversarial input changes. Their solution recasts the task as question answering. Each utterance is paired with one fixed question about its label, and the dialogue history (the previous k−1 utterances) acts as the facts. They extend a Dynamic Memory Network with a hierarchical pyramidal utterance encoder. The model has four parts: utterance encoder, general question module, attentional episodic memory, and act predictor. It is trained adversarially, so it must classify both clean inputs and slightly perturbed ones. In experiments on two benchmarks, Switchboard's DA-annotated conversations and the MapTask dialogues, the authors report better accuracy than state-of-the-art baselines and greater robustness. The work shows that memory over earlier turns and perturbation-based training both help label speaker intent.

## Key points
- Data: the Switchboard dialogue act corpus and the HCRC MapTask corpus, both public.
- Formulation: a conversation C is a sequence of utterances u₁…u_d, each with one DA label from a fixed set. The model predicts the label of u_k from the context H = u₁…u_{k−1}, using a constant question.
- The architecture builds on the DMN of Kumar et al. (2016) and its improved variant. It uses GRU encoders, chosen as a compromise between speed and quality, plus an attention-driven episodic memory updated over several passes.
- Robustness follows the adversarial training of Goodfellow et al. and its text version by Miyato et al. Small worst-case perturbations are added to the input during training to improve robustness and generalization.
- The authors claim this is the first time DA classification has been treated as a QA problem with a DMN. The exact scores are in the experimental section, which is not part of the extracted text.

## Interesting ideas
- The authors turn a labeling task into question answering by attaching one constant question to every input, so a generic reasoning-over-memory architecture can be reused unchanged.
- The model treats earlier turns as memory and attends to them over several passes, reflecting that the previous act constrains the current one (a Question is usually answered, a Greeting is usually returned).
- The encoder is hierarchical and pyramidal, building utterance meaning in stages from words up rather than in one flat pass.
- Adversarial training requires the model to give the same label to an input and its slightly perturbed copy, which improves both robustness and accuracy on clean data.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (answer): Our QA readers could handle internal classification queries (e.g., the act of the current sentence) as ordinary questions over the text world, sharing one explainable answering path.
- **I2** (frames): The speech-act layer in prag could add explicit adjacency rules (Question→Answer, Greeting→Greeting) as a context prior on top of each sentence's own cues, logged as a traceable reason.
- **I3** (frames): Speech-act and frame decisions could be composed bottom-up from UD subtrees (clause, then sentence, then turn), with each level's evidence kept for explanation.
- **I4** (learn): We could build a negative-control and consistency check that perturbs inputs slightly (synonyms, small paraphrases) and flags parser or frame outputs that flip, feeding those cases into repair rules.

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

## Institutions

- [University of Illinois Chicago](https://md.research.elamur.ai/free/en/universities/university-of-illinois-chicago/) — University, Chicago, United States · 38 works · 19,844 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (2): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 401 works · [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 160 works

## Cite

Cite as: Yao Wan, Wenqiang Yan, Jianwei Gao, Zhou Zhao, Jian Wu and Philip S. Yu. 2018. Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training. arXiv:1811.05021.

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

```bibtex
@misc{wan2018improved,
  title = {{Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training}},
  author = {Yao Wan, Wenqiang Yan, Jianwei Gao, Zhou Zhao, Jian Wu and Philip S. Yu},
  year = {2018},
  doi = {10.48550/arxiv.1811.05021},
  eprint = {1811.05021},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1811.05021}
}
```

- [← previous Identifying Explicit Discourse Connectives in German](https://md.research.elamur.ai/free/en/papers/bourgonje-2018-identifying-explicit-discourse-connectives-german/)
- [next → SzegedKoref: A Hungarian Coreference Corpus](https://md.research.elamur.ai/free/en/papers/vincze-2018-szegedkoref-hungarian-coreference-corpus/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/5/)

## References

48 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. D. R. Traum, “Speech acts for dialogue agents,” in Foundations of rational agency. Springer, 1999, pp. 169–201. [↗](https://doi.org/10.1007/978-94-015-9204-8_8)
2. A. Ezen-Can and K. E. Boyer, “Understanding student language: An unsupervised dialogue act classification approach,” Journal of Educational Data Mining (JEDM), vol. 7, no. 1, pp. 51–78, 2015. [↗](https://doi.org/10.5281/zenodo.3554707)
3. N. Reithinger, R. Engel, M. Kipp, and M. Klesen, “Predicting dialogue acts for a speech-to-speech translation system,” in Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on, vol. 2. IEEE, 1996, pp. 654–657. [↗](https://doi.org/10.22028/d291-25293)
4. A. Stolcke, K. Ries, N. Coccaro, E. Shriberg, R. Bates, D. Jurafsky, P. Taylor, R. Martin, C. V. Ess-Dykema, and M. Meteer, “Dialogue act modeling for automatic tagging and recognition of conversational speech,” Computational linguistics, vol. 26, no. 3, pp. 339–373, 2000. [↗](https://doi.org/10.1162/089120100561737) [our card](https://md.research.elamur.ai/free/en/papers/stolcke-2000-dialogue-act-modeling-automatic-tagging/)
5. Z. Chen, R. Yang, Z. Zhao, D. Cai, and X. He, “Dialogue act recognition via crf-attentive structured network,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM, 2018, pp. 225–234. [our card](https://md.research.elamur.ai/free/en/papers/chen-2017-dialogue-act-recognition-crf-attentive/)
6. S. Grau, E. Sanchis, M. J. Castro, and D. Vilar, “Dialogue act classification using a bayesian approach,” in 9th Conference Speech and Computer, 2004. [find](https://scholar.google.com/scholar?q=S%2E+Grau%2C+E%2E+Sanchis%2C+M%2E+J%2E+Castro%2C+and+D%2E+Vilar%2C+%E2%80%9CDialogue+act+classification+using+a+bayesian+approach%2C%E2%80%9D+in+9th+Conference+Speech+and+Computer%2C+2004%2E)
7. H. Khanpour, N. Guntakandla, and R. Nielsen, “Dialogue act classification in domain-independent conversations using a deep recurrent neural network,” in Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2016, pp. 2012–2021. [our card](https://md.research.elamur.ai/free/en/papers/khanpour-2016-dialogue-act-classification-domain-independent/)
8. Y. Ji, G. Haffari, and J. Eisenstein, “A latent variable recurrent neural network for discourse relation language models,” arXiv preprint arXiv:1603.01913, 2016. [↗](https://arxiv.org/abs/1603.01913)
9. T. Miyato, A. M. Dai, and I. Goodfellow, “Adversarial training methods for semi-supervised text classification,” arXiv preprint arXiv:1605.07725, 2016. [↗](https://arxiv.org/abs/1605.07725) [our card](https://md.research.elamur.ai/free/en/papers/miyato-2016-adversarial-training-methods-semi-supervised/)
10. C. Xiong, S. Merity, and R. Socher, “Dynamic memory networks for visual and textual question answering,” international conference on machine learning, pp. 2397–2406, 2016. [↗](https://doi.org/10.48550/arxiv.1603.01417)
11. N. Reithinger and M. Klesen, “Dialogue act classification using language models,” in Fifth European Conference on Speech Communication and Technology, 1997. [find](https://scholar.google.com/scholar?q=N%2E+Reithinger+and+M%2E+Klesen%2C+%E2%80%9CDialogue+act+classification+using+language+models%2C%E2%80%9D+in+Fifth+European+Conference+on+Speech+Communication+and+Technology%2C+1997%2E)
12. J. Geertzen, V. Petukhova, and H. Bunt, “A multidimensional approach to utterance segmentation and dialogue act classification,” in Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue, Antwerp, 2007, pp. 140–149. [our card](https://md.research.elamur.ai/free/en/papers/geertzen-2007-multidimensional-approach-utterance-segmentation-dialogue/)
13. D. Surendran and G.-A. Levow, “Dialog act tagging with support vector machines and hidden markov models,” in Ninth International Conference on Spoken Language Processing, 2006. [find](https://scholar.google.com/scholar?q=D%2E+Surendran+and+G%2E%2DA%2E+Levow%2C+%E2%80%9CDialog+act+tagging+with+support+vector+machines+and+hidden+markov+models%2C%E2%80%9D+in+Ninth+International+Conference+on+Spoken+Language+Processing%2C+2006%2E)
14. N. Kalchbrenner and P. Blunsom, “Recurrent convolutional neural networks for discourse compositionality,” arXiv preprint arXiv:1306.3584, 2013. [↗](https://arxiv.org/abs/1306.3584) [our card](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-convolutional-neural-networks-discourse/)
15. J. Y. Lee and F. Dernoncourt, “Sequential short-text classification with recurrent and convolutional neural networks,” arXiv preprint arXiv:1603.03827, 2016. [↗](https://arxiv.org/abs/1603.03827) [our card](https://md.research.elamur.ai/free/en/papers/lee-2016-sequential-short-text-classification-recurrent/)
16. A. Graves, G. Wayne, and I. Danihelka, “Neural turing machines,” arXiv preprint arXiv:1410.5401, 2014. [↗](https://arxiv.org/abs/1410.5401)
17. D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” arXiv preprint arXiv:1409.0473, 2014. [↗](https://arxiv.org/abs/1409.0473) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
18. Q. You, H. Jin, Z. Wang, C. Fang, and J. Luo, “Image captioning with semantic attention,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4651–4659. [find](https://scholar.google.com/scholar?q=Q%2E+You%2C+H%2E+Jin%2C+Z%2E+Wang%2C+C%2E+Fang%2C+and+J%2E+Luo%2C+%E2%80%9CImage+captioning+with+semantic+attention%2C%E2%80%9D+in+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+2016%2C+pp%2E+4651%E2%80%934659%2E)
19. Y. Wan, Z. Zhao, M. Yang, G. Xu, H. Ying, J. Wu, and P. S. Yu, “Improving automatic source code summarization via deep reinforcement learning,” in Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering. ACM, 2018, pp. 397–407. [↗](https://doi.org/10.48550/arxiv.1811.07234)
20. Z. Zhao, Q. Yang, D. Cai, X. He, and Y. Zhuang, “Video question answering via hierarchical spatio-temporal attention networks,” in International Joint Conference on Artificial Intelligence (IJCAI), vol. 2, 2017, p. 1. [find](https://scholar.google.com/scholar?q=Z%2E+Zhao%2C+Q%2E+Yang%2C+D%2E+Cai%2C+X%2E+He%2C+and+Y%2E+Zhuang%2C+%E2%80%9CVideo+question+answering+via+hierarchical+spatio%2Dtemporal+attention+networks%2C%E2%80%9D+in+International+Joint+Conference+on+Artificial+Intelligence+%28IJCAI%29%2C+vo)
21. B. Pan, H. Li, Z. Zhao, B. Cao, D. Cai, and X. He, “Memen: multi-layer embedding with memory networks for machine comprehension,” arXiv preprint arXiv:1707.09098, 2017. [↗](https://arxiv.org/abs/1707.09098)
22. M.-T. Luong, H. Pham, and C. D. Manning, “Effective approaches to attention-based neural machine translation,” arXiv preprint arXiv:1508.04025, 2015. [↗](https://arxiv.org/abs/1508.04025) [our card](https://md.research.elamur.ai/free/en/papers/luong-2015-effective-approaches-attention-based-neural/)
23. A. Kumar, O. Irsoy, P. Ondruska, M. Iyyer, J. Bradbury, I. Gulrajani, V. Zhong, R. Paulus, and R. Socher, “Ask me anything: Dynamic memory networks for natural language processing,” in International Conference on Machine Learning, 2016, pp. 1378–1387. [↗](https://doi.org/10.48550/arxiv.1506.07285) [our card](https://md.research.elamur.ai/free/en/papers/kumar-2015-ask-me-anything-dynamic-memory/)
24. I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” international conference on learning representations, 2015. [↗](https://doi.org/10.48550/arxiv.1412.6572) [our card](https://md.research.elamur.ai/free/en/papers/goodfellow-2014-explaining-harnessing-adversarial-examples/)
25. F. Tramèr, A. Kurakin, N. Papernot, I. Goodfellow, D. Boneh, and P. McDaniel, “Ensemble adversarial training: Attacks and defenses,” ICLR, 2018. [↗](https://doi.org/10.48550/arxiv.1705.07204)
26. J. Wang, J. Zhang, W. Bao, X. Zhu, B. Cao, and P. S. Yu, “Not just privacy: Improving performance of private deep learning in mobile cloud,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2018, pp. 2407–2416. [↗](https://doi.org/10.48550/arxiv.1809.03428)
27. J. Zhang, J. Wang, L. He, Z. Li, and P. S. Yu, “Layerwise perturbation-based adversarial training for hard drive health degree prediction,” International Conference on Data Mining, 2018. [find](https://scholar.google.com/scholar?q=J%2E+Zhang%2C+J%2E+Wang%2C+L%2E+He%2C+Z%2E+Li%2C+and+P%2E+S%2E+Yu%2C+%E2%80%9CLayerwise+perturbation%2Dbased+adversarial+training+for+hard+drive+health+degree+prediction%2C%E2%80%9D+International+Conference+on+Data+Mining%2C+2018%2E)
28. Y. Wu, D. Bamman, and S. Russell, “Adversarial training for relation extraction,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 1778–1783. [find](https://scholar.google.com/scholar?q=Y%2E+Wu%2C+D%2E+Bamman%2C+and+S%2E+Russell%2C+%E2%80%9CAdversarial+training+for+relation+extraction%2C%E2%80%9D+in+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+2017%2C+pp%2E+1778%E2%80%931783%2E)
29. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014. [find](https://scholar.google.com/scholar?q=N%2E+Srivastava%2C+G%2E+Hinton%2C+A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+R%2E+Salakhutdinov%2C+%E2%80%9CDropout%3A+A+simple+way+to+prevent+neural+networks+from+overfitting%2C%E2%80%9D+The+Journal+of+Machine+Learning+Research%2C+vol%2E+15%2C+no%2E)
30. M. Iyyer, V. Manjunatha, J. Boyd-Graber, and H. Daumé III, “Deep unordered composition rivals syntactic methods for text classification,” in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), vol. 1, 2015, pp. 1681–1691. [our card](https://md.research.elamur.ai/free/en/papers/iyyer-2015-deep-unordered-composition-rivals-syntactic/)
31. Z. Xie, S. I. Wang, J. Li, D. Lévy, A. Nie, D. Jurafsky, and A. Y. Ng, “Data noising as smoothing in neural network language models,” arXiv preprint arXiv:1703.02573, 2017. [↗](https://arxiv.org/abs/1703.02573)
32. Y. Li, T. Cohn, and T. Baldwin, “Robust training under linguistic adversity,” in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, vol. 2, 2017, pp. 21–27. [find](https://scholar.google.com/scholar?q=Y%2E+Li%2C+T%2E+Cohn%2C+and+T%2E+Baldwin%2C+%E2%80%9CRobust+training+under+linguistic+adversity%2C%E2%80%9D+in+Proceedings+of+the+15th+Conference+of+the+European+Chapter+of+the+Association+for+Computational+Linguistics%3A+Volume+2%2C+)
33. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997. [Online]. Available: http://dx.doi.org/10.1162/neco.1997.9.8.1735 [↗](https://doi.org/10.1162/neco.1997.9.8.1735)
34. J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,” arXiv: Neural and Evolutionary Computing, 2014. [find](https://scholar.google.com/scholar?q=J%2E+Chung%2C+C%2E+Gulcehre%2C+K%2E+Cho%2C+and+Y%2E+Bengio%2C+%E2%80%9CEmpirical+evaluation+of+gated+recurrent+neural+networks+on+sequence+modeling%2C%E2%80%9D+arXiv%3A+Neural+and+Evolutionary+Computing%2C+2014%2E)
35. J. Pennington, R. Socher, and C. Manning, “Glove: Global vectors for word representation,” in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, pp. 1532–1543. [our card](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/)
36. H. Kumar, A. Agarwal, R. Dasgupta, S. Joshi, and A. Kumar, “Dialogue act sequence labeling using hierarchical encoder with crf,” arXiv preprint arXiv:1709.04250, 2017. [↗](https://arxiv.org/abs/1709.04250) [our card](https://md.research.elamur.ai/free/en/papers/kumar-2017-dialogue-act-sequence-labeling-using/)
37. W. Chan, N. Jaitly, Q. Le, and O. Vinyals, “Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,” in Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 2016, pp. 4960–4964. [find](https://scholar.google.com/scholar?q=W%2E+Chan%2C+N%2E+Jaitly%2C+Q%2E+Le%2C+and+O%2E+Vinyals%2C+%E2%80%9CListen%2C+attend+and+spell%3A+A+neural+network+for+large+vocabulary+conversational+speech+recognition%2C%E2%80%9D+in+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29%2C+201)
38. K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint arXiv:1406.1078, 2014. [↗](https://arxiv.org/abs/1406.1078)
39. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997. [find](https://scholar.google.com/scholar?q=S%2E+Hochreiter+and+J%2E+Schmidhuber%2C+%E2%80%9CLong+short%2Dterm+memory%2C%E2%80%9D+Neural+computation%2C+vol%2E+9%2C+no%2E+8%2C+pp%2E+1735%E2%80%931780%2C+1997%2E)
40. B. Peng, Z. Lu, H. Li, and K.-F. Wong, “Towards neural network-based reasoning,” arXiv preprint arXiv:1508.05508, 2015. [↗](https://arxiv.org/abs/1508.05508)
41. D. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014. [↗](https://arxiv.org/abs/1412.6980)
42. J. J. Godfrey, E. C. Holliman, and J. McDaniel, “Switchboard: Telephone speech corpus for research and development,” in Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on, vol. 1. IEEE, 1992, pp. 517–520. [find](https://scholar.google.com/scholar?q=J%2E+J%2E+Godfrey%2C+E%2E+C%2E+Holliman%2C+and+J%2E+McDaniel%2C+%E2%80%9CSwitchboard%3A+Telephone+speech+corpus+for+research+and+development%2C%E2%80%9D+in+Acoustics%2C+Speech%2C+and+Signal+Processing%2C+1992%2E+ICASSP%2D92%2E%2C+1992+IEEE+Internatio)
43. A. H. Anderson, M. Bader, E. G. Bard, E. Boyle, G. Doherty, S. Garrod, S. Isard, J. Kowtko, J. McAllister, J. Miller et al., “The hcrc map task corpus,” Language and speech, vol. 34, no. 4, pp. 351–366, 1991. [↗](https://doi.org/10.1177/002383099103400404)
44. Y. Liu, K. Han, Z. Tan, and Y. Lei, “Using context information for dialog act classification in dnn framework,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 2170–2178. [our card](https://md.research.elamur.ai/free/en/papers/liu-2017-context-information-dialog-act-classification/)
45. Q. H. Tran, I. Zukerman, and G. Haffari, “Preserving distributional information in dialogue act classification,” Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2151–2156, 2017. [our card](https://md.research.elamur.ai/free/en/papers/tran-2017-preserving-distributional-information-dialogue-act/)
46. Y. Ji, G. Haffari, and J. Eisenstein, “A latent variable recurrent neural network for discourse relation language models,” north american chapter of the association for computational linguistics, pp. 332–342, 2016. [↗](https://doi.org/10.48550/arxiv.1603.01913)
47. F. N. Julia, K. M. Iftekharuddin, and A. U. ISLAM, “Dialog act classification using acoustic and discourse information of maptask data,” International Journal of Computational Intelligence and Applications, vol. 9, no. 04, pp. 289–311, 2010. [↗](https://doi.org/10.1142/s1469026810002926)
48. Q. H. Tran, G. Haffari, and I. Zukerman, “A generative attentional neural network model for dialogue act classification,” in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), vol. 2, 2017, pp. 524–529. [our card](https://md.research.elamur.ai/free/en/papers/tran-2017-generative-attentional-neural-network-model/)

*Updated 24 October 2026*