---
title: "Modeling Local Contexts for Joint Dialogue Act — Li 2020"
description: "The paper addresses the problem of identifying dialogue acts (DAR) and classifying sentiment (SC) together within a single model."
authors: ["Jingye Li", "Hao Fei", "Donghong Ji"]
year: 2020
venue: "Proceedings of the 28th International Conference on Computational Linguistics"
source: "https://aclanthology.org/2020.coling-main.53/"
doi: "10.18653/v1/2020.coling-main.53"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/li-2020-modeling-local-contexts-joint-dialogue/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/li-2020-modeling-local-contexts-joint-dialogue/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2020](https://md.research.elamur.ai/free/papers/2020/page/3/) / Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions

# Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions

**Authors:** Jingye Li, Hao Fei, Donghong Ji · **Year:** 2020 · **Venue:** Proceedings of the 28th International Conference on Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.coling-main.53/) · [PDF](https://aclanthology.org/2020.coling-main.53.pdf) · [DOI 10.18653/v1/2020.coling-main.53](https://doi.org/10.18653/v1/2020.coling-main.53) · [OpenAlex](https://openalex.org/W3117904889)

**Citations:** 17 citations (openalex-snapshot · 2026-10-14) · [8](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper addresses the problem of identifying dialogue acts (DAR) and classifying sentiment (SC) together within a single model. Both are framed as sequence labeling over the utterances of a conversation. Earlier joint systems relied on recurrent encoders such as LSTM. The authors argue that these encoders underuse local context, because nearby utterances in a dialogue carry the most useful cues about acts and sentiment shifts.

Their framework has three layers:
- A BiLSTM with sinusoidal position embeddings encodes each utterance.
- Stacked convolutional layers capture dialogue context.
- Separate linear outputs predict labels for each task.

For the context layers, they first adopt dynamic convolutions (DCN). They then propose a context-aware variant (CDCN), which generates kernels from a window of neighboring utterances rather than from the current input alone. Both are extended to bi-channel versions (BDCN, BCDCN), with one channel per task and latent cross-channel interaction, trained jointly under multi-task learning. DiaBERT supplies dialogue-level pretrained representations.

On the Mastodon and DailyDialog benchmarks, BCDCN reaches state-of-the-art results. This supports the value of explicit local-context modeling for joint dialogue understanding.

## Key points
- **Data and code:** Experiments use the Mastodon and DailyDialog benchmarks, and the code is released at github.com/ljynlp/BCDCN. Both BDCN and BCDCN beat prior baselines, including DCR-Net, by clear margins, with BCDCN performing best.
- **Why DiaBERT:** Standard BERT accepts at most two sentence segments, so the authors use DiaBERT (Liu and Lapata, 2019) to encode whole multi-utterance dialogues.
- **DiaBERT vs. BERT:** DiaBERT helps more on the larger DailyDialog set. On small Mastodon, BERT gives the bigger gain. In data-scale tests on DailyDialog, BERT wins when fewer than 20% of training examples are used for fine-tuning.
- **Ablations on DailyDialog:** Performance drops when any of these components is removed or replaced:
  - position embeddings;
  - cross-channel interaction;
  - the dynamic kernel;
  - the context-aware convolution (swapped for vanilla, depth-wise, or plain dynamic convolution).

  A fixed 0.5/0.5 loss weighting also performs worse than homoscedastic-uncertainty weighting.
- **Kernel visualizations:** Each channel attends to its own task while also drawing on the other channel. BCDCN shows more activated kernel weights than BDCN.

*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

8 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 7 not yet.

- [COMICORDA: Dialogue Act Recognition in Comic Books](https://md.research.elamur.ai/free/papers/martinek-2024-comicorda-dialogue-act-recognition-comic/)

## Cite

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

```bibtex
@inproceedings{li2020modeling,
  title = {{Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions}},
  author = {Li, Jingye and Fei, Hao and Ji, Donghong},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.53},
  url = {https://doi.org/10.18653/v1/2020.coling-main.53}
}
```

- [← previous Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection](https://md.research.elamur.ai/free/papers/pan-2020-modeling-intra-inter-modality-incongruity/)
- [next → Morphological Analysis and Disambiguation for Gulf Arabic: The Interplay between Resources and Methods](https://md.research.elamur.ai/free/papers/lingbulk-2020-khalifa-morphological-analysis-disambiguation-gulf-arabic/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/papers/2020/page/3/)

## References

33 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Reinald Kim Amplayo, Jihyeok Kim, Sua Sung, and Seung-won Hwang. 2018. Cold-start aware user and product attention for sentiment classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2535–2544. Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. arXiv:1607.06450. 2016. Layer normalization. arXiv preprint Christophe Cerisara, Somayeh Jafaritazehjani, Adedayo Oluokun, and Hoa Le. 2018. Multi-task dialog act and sentiment recognition on mastodon. In Proceedings of COLING, pages 745–754. [↗](https://arxiv.org/abs/1607.06450) [our card](https://md.research.elamur.ai/free/papers/ba-2016-layer-normalization/)
2. Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, and Xiaofei He. 2018. Dialogue act recognition via crf-attentive structured network. In Proceedings of SIGIR, pages 225–234. [find](https://scholar.google.com/scholar?q=Zheqian+Chen%2C+Rongqin+Yang%2C+Zhou+Zhao%2C+Deng+Cai%2C+and+Xiaofei+He%2E+2018%2E+Dialogue+act+recognition+via+crf%2Dattentive+structured+network%2E+In+Proceedings+of+SIGIR%2C+pages+225%E2%80%93234%2E)
3. Pierre Colombo, Emile Chapuis, Matteo Manica, Emmanuel Vignon, Giovanna Varni, and Chloe Clavel. 2020. Guiding attention in sequence-to-sequence models for dialogue act prediction. In Proceedings of AAAI, pages 7594–7601. [↗](https://doi.org/10.48550/arxiv.2002.08801)
4. Alexis Conneau, Holger Schwenk, Loı̈c Barrault, and Yann Lecun. 2017. Very deep convolutional networks for text classification. In Proceedings of EACL, pages 1107–1116. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Holger+Schwenk%2C+Lo%C4%B1%CC%88c+Barrault%2C+and+Yann+Lecun%2E+2017%2E+Very+deep+convolutional+networks+for+text+classification%2E+In+Proceedings+of+EACL%2C+pages+1107%E2%80%931116%2E)
5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186. [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+4171%E2%80%934186%2E)
6. Hao Fei, Yafeng Ren, and Donghong Ji. 2019. Implicit objective network for emotion detection. In Proceedings of NLPCC, pages 647–659. [find](https://scholar.google.com/scholar?q=Hao+Fei%2C+Yafeng+Ren%2C+and+Donghong+Ji%2E+2019%2E+Implicit+objective+network+for+emotion+detection%2E+In+Proceedings+of+NLPCC%2C+pages+647%E2%80%93659%2E)
7. Hao Fei, Meishan Zhang, and Donghong Ji. 2020a. Cross-lingual semantic role labeling with high-quality translated training corpus. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7014–7026. [find](https://scholar.google.com/scholar?q=Hao+Fei%2C+Meishan+Zhang%2C+and+Donghong+Ji%2E+2020a%2E+Cross%2Dlingual+semantic+role+labeling+with+high%2Dquality+translated+training+corpus%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Comp)
8. Hao Fei, Yue Zhang, Yafeng Ren, and Donghong Ji. 2020b. Latent emotion memory for multi-label emotion classification. In Proceedings of AAAI, pages 7692–7699. [find](https://scholar.google.com/scholar?q=Hao+Fei%2C+Yue+Zhang%2C+Yafeng+Ren%2C+and+Donghong+Ji%2E+2020b%2E+Latent+emotion+memory+for+multi%2Dlabel+emotion+classification%2E+In+Proceedings+of+AAAI%2C+pages+7692%E2%80%937699%2E)
9. Nobuo Inui, Toshiaki Ebe, Bipin Indurkhya, and Yoshiyuki Kotani. 2001. A case-based natural language dialogue system using dialogue act. In Proceedings of SMC, pages 193–198. [find](https://scholar.google.com/scholar?q=Nobuo+Inui%2C+Toshiaki+Ebe%2C+Bipin+Indurkhya%2C+and+Yoshiyuki+Kotani%2E+2001%2E+A+case%2Dbased+natural+language+dialogue+system+using+dialogue+act%2E+In+Proceedings+of+SMC%2C+pages+193%E2%80%93198%2E)
10. Chen Jia, Xiaobo Liang, and Yue Zhang. 2019. Cross-domain NER using cross-domain language modeling. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2464–2474. [find](https://scholar.google.com/scholar?q=Chen+Jia%2C+Xiaobo+Liang%2C+and+Yue+Zhang%2E+2019%2E+Cross%2Ddomain+NER+using+cross%2Ddomain+language+modeling%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+24)
11. Lukasz Kaiser, Aidan N Gomez, and Francois Chollet. 2018. Depthwise separable convolutions for neural machine translation. In Proceedings of ICLR. [↗](https://doi.org/10.48550/arxiv.1706.03059)
12. Nal Kalchbrenner and Phil Blunsom. 2013. Recurrent convolutional neural networks for discourse compositionality. arXiv preprint arXiv:1306.3584. [↗](https://arxiv.org/abs/1306.3584) [our card](https://md.research.elamur.ai/free/papers/kalchbrenner-2013-recurrent-convolutional-neural-networks-discourse/)
13. Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A convolutional neural network for modelling sentences. In Proceedings of ACL, pages 655–665. [↗](https://doi.org/10.48550/arxiv.1404.2188) [our card](https://md.research.elamur.ai/free/papers/kalchbrenner-2014-convolutional-neural-network-modelling-sentences/)
14. Simon Keizer, Rieks op den Akker, and Anton Nijholt. 2002. Dialogue act recognition with bayesian networks for dutch dialogues. In Proceedings of SIGDIAL Workshop on Discourse and Dialogue, pages 88–94. [find](https://scholar.google.com/scholar?q=Simon+Keizer%2C+Rieks+op+den+Akker%2C+and+Anton+Nijholt%2E+2002%2E+Dialogue+act+recognition+with+bayesian+networks+for+dutch+dialogues%2E+In+Proceedings+of+SIGDIAL+Workshop+on+Discourse+and+Dialogue%2C+pages+88%E2%80%939) [our card](https://md.research.elamur.ai/free/papers/keizer-2002-dialogue-act-recognition-bayesian-networks/)
15. Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of CVPR, pages 7482–7491. [find](https://scholar.google.com/scholar?q=Alex+Kendall%2C+Yarin+Gal%2C+and+Roberto+Cipolla%2E+2018%2E+Multi%2Dtask+learning+using+uncertainty+to+weigh+losses+for+scene+geometry+and+semantics%2E+In+Proceedings+of+CVPR%2C+pages+7482%E2%80%937491%2E)
16. Minkyoung Kim and Harksoo Kim. 2018. Integrated neural network model for identifying speech acts, predicators, and sentiments of dialogue utterances. Pattern Recognition Letters., 101:1–5. [↗](https://doi.org/10.1016/j.patrec.2017.11.009)
17. Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of EMNLP, pages 1746–1751. [find](https://scholar.google.com/scholar?q=Yoon+Kim%2E+2014%2E+Convolutional+neural+networks+for+sentence+classification%2E+In+Proceedings+of+EMNLP%2C+pages+1746%E2%80%931751%2E) [our card](https://md.research.elamur.ai/free/papers/kim-2014-convolutional-neural-networks-sentence-classification/)
18. Harshit Kumar, Arvind Agarwal, Riddhiman Dasgupta, and Sachindra Joshi. 2018. Dialogue act sequence labeling using hierarchical encoder with CRF. In Proceedings of AAAI, pages 3440–3447. [↗](https://doi.org/10.1609/aaai.v32i1.11701) [our card](https://md.research.elamur.ai/free/papers/kumar-2017-dialogue-act-sequence-labeling-using/)
19. Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2015. Molding cnns for text: non-linear, non-consecutive convolutions. In Proceedings of EMNLP, pages 1565–1575. [find](https://scholar.google.com/scholar?q=Tao+Lei%2C+Regina+Barzilay%2C+and+Tommi+Jaakkola%2E+2015%2E+Molding+cnns+for+text%3A+non%2Dlinear%2C+non%2Dconsecutive+convolutions%2E+In+Proceedings+of+EMNLP%2C+pages+1565%E2%80%931575%2E)
20. Piroska Lendvai and Jeroen Geertzen. 2007. Token-based chunking of turn-internal dialogue act sequences. In Proceedings of SIGDIAL, pages 174–181. [find](https://scholar.google.com/scholar?q=Piroska+Lendvai+and+Jeroen+Geertzen%2E+2007%2E+Token%2Dbased+chunking+of+turn%2Dinternal+dialogue+act+sequences%2E+In+Proceedings+of+SIGDIAL%2C+pages+174%E2%80%93181%2E) [our card](https://md.research.elamur.ai/free/papers/lendvai-2007-token-based-chunking-turn-internal/)
21. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. Dailydialog: A manually labelled multi-turn dialogue dataset. In Proceedings of IJCNLP, pages 986–995. [↗](https://doi.org/10.48550/arxiv.1710.03957) [our card](https://md.research.elamur.ai/free/papers/li-2017-dailydialog-manually-labelled-multi-turn/)
22. Yang Liu and Mirella Lapata. 2019. Text summarization with pretrained encoders. In Proceedings of EMNLP-IJCNLP, pages 3728–3738. [↗](https://doi.org/10.48550/arxiv.1908.08345)
23. Navonil Majumder, Soujanya Poria, Devamanyu Hazarika, Rada Mihalcea, Alexander Gelbukh, and Erik Cambria. 2019. Dialoguernn: An attentive RNN for emotion detection in conversations. In Proceedings of AAAI, pages 6818–6825. [↗](https://doi.org/10.1609/aaai.v33i01.33016818)
24. Chao Qiao, Bo Huang, Guocheng Niu, Daren Li, Daxiang Dong, Wei He, Dianhai Yu, and Hua Wu. 2018. A new method of region embedding for text classification. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=Chao+Qiao%2C+Bo+Huang%2C+Guocheng+Niu%2C+Daren+Li%2C+Daxiang+Dong%2C+Wei+He%2C+Dianhai+Yu%2C+and+Hua+Wu%2E+2018%2E+A+new+method+of+region+embedding+for+text+classification%2E+In+Proceedings+of+ICLR%2E)
25. Libo Qin, Wanxiang Che, Yangming Li, Minheng Ni, and Ting Liu. 2020. Dcr-net: A deep co-interactive relation network for joint dialog act recognition and sentiment classification. In Proceedings of AAAI, pages 8665–8672. [find](https://scholar.google.com/scholar?q=Libo+Qin%2C+Wanxiang+Che%2C+Yangming+Li%2C+Minheng+Ni%2C+and+Ting+Liu%2E+2020%2E+Dcr%2Dnet%3A+A+deep+co%2Dinteractive+relation+network+for+joint+dialog+act+recognition+and+sentiment+classification%2E+In+Proceedings+of+AA)
26. Vipul Raheja and Joel Tetreault. 2019. Dialogue act classification with context-aware self-attention. In Proceedings of NAACL-HLT, pages 3727–3733. [↗](https://doi.org/10.48550/arxiv.1904.02594) [our card](https://md.research.elamur.ai/free/papers/raheja-2019-dialogue-act-classification-context-aware/)
27. Yafeng Ren, Yue Zhang, Meishan Zhang, and Donghong Ji. 2016. Improving twitter sentiment classification using topic-enriched multi-prototype word embeddings. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pages 3038–3044. [find](https://scholar.google.com/scholar?q=Yafeng+Ren%2C+Yue+Zhang%2C+Meishan+Zhang%2C+and+Donghong+Ji%2E+2016%2E+Improving+twitter+sentiment+classification+using+topic%2Denriched+multi%2Dprototype+word+embeddings%2E+In+Proceedings+of+the+Thirtieth+AAAI+Confe)
28. Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Carol Van Ess-Dykema, and Marie Meteer. 2000. Dialogue act modeling for automatic tagging and recognition of conversational speech. Computational linguistics, 26(3):339–373. [↗](https://doi.org/10.1162/089120100561737) [our card](https://md.research.elamur.ai/free/papers/prag-2000-stolcke-dialogue-act-modeling-automatic-tagging/)
29. Dinoj Surendran and Gina-Anne Levow. 2006. Dialog act tagging with support vector machines and hidden markov models. In Proceedings of InterSpeech. [find](https://scholar.google.com/scholar?q=Dinoj+Surendran+and+Gina%2DAnne+Levow%2E+2006%2E+Dialog+act+tagging+with+support+vector+machines+and+hidden+markov+models%2E+In+Proceedings+of+InterSpeech%2E)
30. Maryam Tavafi, Yashar Mehdad, Shafiq Joty, Giuseppe Carenini, and Raymond Ng. 2013. Dialogue act recognition in synchronous and asynchronous conversations. In Proceedings of SIGDIAL, pages 117–121. [↗](https://doi.org/10.14288/1.0052186) [our card](https://md.research.elamur.ai/free/papers/tavafi-2013-dialogue-act-recognition-synchronous-asynchronous/)
31. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of NeurIPS, pages 5998–6008. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N+Gomez%2C+%C5%81ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+Proceedings+of+NeurIPS%2C+pages+5998%E2%80%936008)
32. Felix Wu, Angela Fan, Alexei Baevski, Yann N Dauphin, and Michael Auli. 2019. Pay less attention with lightweight and dynamic convolutions. In Proceedings of ICLR. [↗](https://doi.org/10.48550/arxiv.1901.10430) [our card](https://md.research.elamur.ai/free/papers/wu-2019-pay-less-attention-lightweight-dynamic/)
33. Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level convolutional networks for text classification. In Proceedings of NeurIPS, pages 649–657. [↗](https://doi.org/10.48550/arxiv.1509.01626) [our card](https://md.research.elamur.ai/free/papers/zhang-2015-character-level-convolutional-networks-text/)