---
title: "Zero-shot User Intent Detection via Capsule Neural Networks"
description: "The authors study this zero-shot intent detection setting, where the emerging intents do not overlap… 25 references, cited by 67 papers here."
authors: ["Congying Xia", "Chenwei Zhang", "Xiaohui Yan", "Yi Chang", "Philip Yu"]
year: 2018
venue: "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D18-1348/"
doi: "10.18653/v1/d18-1348"
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/en/papers/xia-2018-zero-shot-user-intent-detection/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xia-2018-zero-shot-user-intent-detection/)

[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/2/) / Zero-shot User Intent Detection via Capsule Neural Networks

# Zero-shot User Intent Detection via Capsule Neural Networks

**Authors:** Congying Xia, [Chenwei Zhang](https://md.research.elamur.ai/free/en/authors/chenwei-zhang/), Xiaohui Yan, [Yi Chang](https://md.research.elamur.ai/free/en/authors/yi-chang/) and [Philip Yu](https://md.research.elamur.ai/free/en/authors/philip-s-yu/) · **Year:** 2018 · **Venue:** [Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2018](https://md.research.elamur.ai/free/en/venues/emnlp/2018/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/D18-1348/) · [PDF](https://aclanthology.org/D18-1348.pdf) · [DOI 10.18653/v1/d18-1348](https://doi.org/10.18653/v1/d18-1348) · [OpenAlex](https://openalex.org/W2964071174)

**Citations:** 195 citations (OpenAlex, 2026-10-14) · [67](https://md.research.elamur.ai/free/en/papers/xia-2018-zero-shot-user-intent-detection/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Voice assistants keep gaining new skills, so intent classifiers often meet user intents with no annotated utterances yet. The authors study this zero-shot intent detection setting, where the emerging intents do not overlap with the training intents. They adapt capsule networks to text in a model called IntentCapsNet. Its SemanticCaps layer, a bidirectional LSTM with multi-head self-attention, extracts separate semantic features of an utterance, such as an action or an entity name. Its DetectionCaps layer merges these features through dynamic routing-by-agreement into one activation vector per intent. The zero-shot extension, IntentCapsNet-ZSL, builds Zero-shot DetectionCaps for unseen intents from three sources: the trained SemanticCaps, the routing learned on known intents, and similarities between intent label embeddings. It needs no label ontologies or hand-defined attributes. Experiments on SNIPS-NLU and CVA show that the models handle diversely phrased known intents better and can recognize new intents without labeled examples. Attention analyses also make the model's behaviour easier to interpret. The work matters because it lets dialog systems grow cheaply, without new annotation or full retraining.

## Key points
- The model has three capsule types: SemanticCaps (feature extraction), DetectionCaps (aggregation for known intents) and Zero-shot DetectionCaps (emerging intents). Word inputs are skip-gram embeddings.
- At inference, vote vectors computed for existing intents are transferred to emerging ones. The transfer is weighted by label-embedding similarity, for example from PlayMusic to AddToPlaylist.
- The model is evaluated on two real-world datasets, SNIPS-NLU and CVA. The CVA analysis covers 20 emerging intents.
- On CVA, 13 of the 20 emerging intents have a high-variance similarity distribution (var(q_l) > 0.005), and all of these reach accuracy ≥ 0.83. A low variance does not always mean poor results.
- Attention heads carry over across intents. The head that tracks the "play" action in PlayMusic also highlights rating actions in the unseen RateABook intent.

*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
- [Jilin University](https://md.research.elamur.ai/free/en/universities/jilin-university/) — University, Changchun, China · 8 works · 5,204 citations

Also on the byline: [Huawei Technologies (United States)](https://ror.org/03jyqk712).

📚 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

## Cite

Cite as: Congying Xia, Chenwei Zhang, Xiaohui Yan, Yi Chang and Philip Yu. 2018. Zero-shot User Intent Detection via Capsule Neural Networks. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{xia2018zero,
  title = {{Zero-shot User Intent Detection via Capsule Neural Networks}},
  author = {Congying Xia, Chenwei Zhang, Xiaohui Yan, Yi Chang and Philip Yu},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  year = {2018},
  doi = {10.18653/v1/d18-1348},
  url = {https://doi.org/10.18653/v1/d18-1348}
}
```

- [← previous Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised](https://md.research.elamur.ai/free/en/papers/angelidis-2018-summarizing-opinions-aspect-extraction-meets/)
- [next → Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge](https://md.research.elamur.ai/free/en/papers/mihaylov-2018-knowledgeable-reader-enhancing-cloze-style/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/)

## References

25 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, and Fei Sha. 2016. Synthesized classifiers for zero-shot learning. In CVPR, pages 5327–5336. [find](https://scholar.google.com/scholar?q=Soravit+Changpinyo%2C+Wei%2DLun+Chao%2C+Boqing+Gong%2C+and+Fei+Sha%2E+2016%2E+Synthesized+classifiers+for+zero%2Dshot+learning%2E+In+CVPR%2C+pages+5327%E2%80%935336%2E)
2. Yun-Nung Chen, Dilek Hakkani-Tür, and Xiaodong He. 2016a. Zero-shot learning of intent embeddings for expansion by convolutional deep structured semantic models. In ICASSP, pages 6045–6049. [find](https://scholar.google.com/scholar?q=Yun%2DNung+Chen%2C+Dilek+Hakkani%2DTu%CC%88r%2C+and+Xiaodong+He%2E+2016a%2E+Zero%2Dshot+learning+of+intent+embeddings+for+expansion+by+convolutional+deep+structured+semantic+models%2E+In+ICASSP%2C+pages+6045%E2%80%936049%2E)
3. Yun-Nung Chen, Dilek Hakkani-Tür, Gökhan Tür, Jianfeng Gao, and Li Deng. 2016b. End-to-end memory networks with knowledge carryover for multi-turn spoken language understanding. In IN-TERSPEECH, pages 3245–3249. [find](https://scholar.google.com/scholar?q=Yun%2DNung+Chen%2C+Dilek+Hakkani%2DTu%CC%88r%2C+Go%CC%88khan+Tu%CC%88r%2C+Jianfeng+Gao%2C+and+Li+Deng%2E+2016b%2E+End%2Dto%2Dend+memory+networks+with+knowledge+carryover+for+multi%2Dturn+spoken+language+understanding%2E+In+IN%2DTERSPEECH%2C+pa)
4. Emmanuel Ferreira, Bassam Jabaian, and Fabrice Lefevre. 2015a. Online adaptative zero-shot learning spoken language understanding using word-embedding. In ICASSP, pages 5321–5325. [find](https://scholar.google.com/scholar?q=Emmanuel+Ferreira%2C+Bassam+Jabaian%2C+and+Fabrice+Lefevre%2E+2015a%2E+Online+adaptative+zero%2Dshot+learning+spoken+language+understanding+using+word%2Dembedding%2E+In+ICASSP%2C+pages+5321%E2%80%935325%2E)
5. Emmanuel Ferreira, Bassam Jabaian, and Fabrice Lefèvre. 2015b. Zero-shot semantic parser for spoken language understanding. In INTERSPEECH, pages 1403–1407. [find](https://scholar.google.com/scholar?q=Emmanuel+Ferreira%2C+Bassam+Jabaian%2C+and+Fabrice+Lefe%CC%80vre%2E+2015b%2E+Zero%2Dshot+semantic+parser+for+spoken+language+understanding%2E+In+INTERSPEECH%2C+pages+1403%E2%80%931407%2E)
6. Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Tomas Mikolov, et al. 2013. Devise: A deep visual-semantic embedding model. In NIPS, pages 2121–2129. [find](https://scholar.google.com/scholar?q=Andrea+Frome%2C+Greg+S+Corrado%2C+Jon+Shlens%2C+Samy+Bengio%2C+Jeff+Dean%2C+Tomas+Mikolov%2C+et+al%2E+2013%2E+Devise%3A+A+deep+visual%2Dsemantic+embedding+model%2E+In+NIPS%2C+pages+2121%E2%80%932129%2E)
7. Geoffrey E Hinton, Alex Krizhevsky, and Sida D Wang. 2011. Transforming auto-encoders. In ICANN, pages 44–51. [find](https://scholar.google.com/scholar?q=Geoffrey+E+Hinton%2C+Alex+Krizhevsky%2C+and+Sida+D+Wang%2E+2011%2E+Transforming+auto%2Dencoders%2E+In+ICANN%2C+pages+44%E2%80%9351%2E)
8. Sepp Hochreiter and Jürgen Schmidhuber. 1997. [Long short-term memory](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/). Neural computation, 9(8):1735–1780. representations in vector space. arXiv:1301.3781.
9. Matthew B Hoy. 2018. Alexa, siri, cortana, and more: An introduction to voice assistants. Medical reference services quarterly, 37(1):81–88. [find](https://scholar.google.com/scholar?q=Matthew+B+Hoy%2E+2018%2E+Alexa%2C+siri%2C+cortana%2C+and+more%3A+An+introduction+to+voice+assistants%2E+Medical+reference+services+quarterly%2C+37%281%29%3A81%E2%80%9388%2E)
10. Jian Hu, Gang Wang, Fred Lochovsky, Jian-tao Sun, and Zheng Chen. 2009. Understanding user’s query intent with wikipedia. In WWW, pages 471–480. [find](https://scholar.google.com/scholar?q=Jian+Hu%2C+Gang+Wang%2C+Fred+Lochovsky%2C+Jian%2Dtao+Sun%2C+and+Zheng+Chen%2E+2009%2E+Understanding+user%E2%80%99s+query+intent+with+wikipedia%2E+In+WWW%2C+pages+471%E2%80%93480%2E)
11. Yoon Kim. 2014. [Convolutional neural networks for sentence classification](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/). arXiv preprint arXiv:1408.5882. arXiv preprint Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. 2017. Dynamic routing between capsules. In NIPS, pages 3859–3869.
12. Mike Schuster and Kuldip K Paliwal. 1997. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11):2673–2681. [find](https://scholar.google.com/scholar?q=Mike+Schuster+and+Kuldip+K+Paliwal%2E+1997%2E+Bidirectional+recurrent+neural+networks%2E+IEEE+Transactions+on+Signal+Processing%2C+45%2811%29%3A2673%E2%80%932681%2E)
13. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. [find](https://scholar.google.com/scholar?q=Diederik+P+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+method+for+stochastic+optimization%2E+arXiv+preprint+arXiv%3A1412%2E6980%2E)
14. Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In NIPS, pages 935– 943. [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Milind+Ganjoo%2C+Christopher+D+Manning%2C+and+Andrew+Ng%2E+2013%2E+Zero%2Dshot+learning+through+cross%2Dmodal+transfer%2E+In+NIPS%2C+pages+935%E2%80%93+943%2E)
15. Anjishnu Kumar, Pavankumar Reddy Muddireddy, Markus Dreyer, and Björn Hoffmeister. 2017. Zero-shot learning across heterogeneous overlapping domains. In INTERSPEECH, volume 2017, pages 2914–2918. [find](https://scholar.google.com/scholar?q=Anjishnu+Kumar%2C+Pavankumar+Reddy+Muddireddy%2C+Markus+Dreyer%2C+and+Bjo%CC%88rn+Hoffmeister%2E+2017%2E+Zero%2Dshot+learning+across+heterogeneous+overlapping+domains%2E+In+INTERSPEECH%2C+volume+2017%2C+pages+2914%E2%80%932918%2E)
16. Duyu Tang, Bing Qin, and Ting Liu. 2015. [Document modeling with gated recurrent neural network for sentiment classification](https://md.research.elamur.ai/free/en/papers/tang-2015-document-modeling-gated-recurrent-neural/). In EMNLP, pages 1422– 1432.
17. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML, pages 282–289. [find](https://scholar.google.com/scholar?q=John+D%2E+Lafferty%2C+Andrew+McCallum%2C+and+Fernando+C%2E+N%2E+Pereira%2E+2001%2E+Conditional+random+fields%3A+Probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+ICML%2C+pages+282%E2%80%93289%2E)
18. Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. 2014. Attribute-based classification for zero-shot visual object categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3):453–465. [find](https://scholar.google.com/scholar?q=Christoph+H+Lampert%2C+Hannes+Nickisch%2C+and+Stefan+Harmeling%2E+2014%2E+Attribute%2Dbased+classification+for+zero%2Dshot+visual+object+categorization%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intellige)
19. Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos, Mo Yu, Bing Xiang, Bowen Zhou, and Yoshua Bengio. 2017. [A structured self-attentive sentence embedding](https://md.research.elamur.ai/free/en/papers/lin-2017-structured-self-attentive-sentence-embedding/). In ICLR.
20. Bing Liu and Ian Lane. 2016. Attention-based recurrent neural network models for joint intent detection and slot filling. In INTERSPEECH, pages 685–689. [find](https://scholar.google.com/scholar?q=Bing+Liu+and+Ian+Lane%2E+2016%2E+Attention%2Dbased+recurrent+neural+network+models+for+joint+intent+detection+and+slot+filling%2E+In+INTERSPEECH%2C+pages+685%E2%80%93689%2E)
21. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In NIPS, pages 6000–6010.
22. IBM Watson Assistant. 2017. Defining intents. In [https://console.bluemix.net/docs/](https://console.bluemix.net/docs/) services/conversation/intents. html\#defining-intents. [↗](https://console.bluemix.net/docs/)
23. Puyang Xu and Ruhi Sarikaya. 2013. Convolutional neural network based triangular crf for joint intent detection and slot filling. In ASRU, pages 78–83. [find](https://scholar.google.com/scholar?q=Puyang+Xu+and+Ruhi+Sarikaya%2E+2013%2E+Convolutional+neural+network+based+triangular+crf+for+joint+intent+detection+and+slot+filling%2E+In+ASRU%2C+pages+78%E2%80%9383%2E)
24. Majid Yazdani and James Henderson. 2015. A model of zero-shot learning of spoken language understanding. In EMNLP, pages 244–249. [find](https://scholar.google.com/scholar?q=Majid+Yazdani+and+James+Henderson%2E+2015%2E+A+model+of+zero%2Dshot+learning+of+spoken+language+understanding%2E+In+EMNLP%2C+pages+244%E2%80%93249%2E)
25. Chenwei Zhang, Wei Fan, Nan Du, and Philip S Yu. 2016. Mining user intentions from medical queries: A neural network based heterogeneous jointly modeling approach. In WWW, pages 1373–1384. [find](https://scholar.google.com/scholar?q=Chenwei+Zhang%2C+Wei+Fan%2C+Nan+Du%2C+and+Philip+S+Yu%2E+2016%2E+Mining+user+intentions+from+medical+queries%3A+A+neural+network+based+heterogeneous+jointly+modeling+approach%2E+In+WWW%2C+pages+1373%E2%80%931384%2E)

*Updated 24 October 2026*