---
title: "Sequence-to-Sequence Data Augmentation for Dialogue"
description: "Slot-filling modules in task-oriented dialogue systems struggle when a new domain has only a few… 46 references, cited by 64 papers here."
authors: ["Yutai Hou", "Yijia Liu", "Wanxiang Che", "Ting Liu"]
year: 2018
venue: "Proceedings of the 27th International Conference on Computational Linguistics"
source: "https://aclanthology.org/C18-1105/"
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/hou-2018-sequence-sequence-data-augmentation-dialogue/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hou-2018-sequence-sequence-data-augmentation-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/4/) / Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding

# Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding

**Authors:** [Yutai Hou](https://md.research.elamur.ai/free/en/authors/yutai-hou/), [Yijia Liu](https://md.research.elamur.ai/free/en/authors/yijia-liu/), [Wanxiang Che](https://md.research.elamur.ai/free/en/authors/wanxiang-che/) and [Ting Liu](https://md.research.elamur.ai/free/en/authors/ting-liu/) · **Year:** 2018 · **Venue:** [Proceedings of the 27th International Conference on Computational Linguistics](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2018](https://md.research.elamur.ai/free/en/venues/coling/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/C18-1105/) · [PDF](https://aclanthology.org/C18-1105.pdf) · [OpenAlex](https://openalex.org/W2810809989)

**Citations:** 23 citations (OpenAlex, 2026-10-14) · [64](https://md.research.elamur.ai/free/en/papers/hou-2018-sequence-sequence-data-augmentation-dialogue/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Slot-filling modules in task-oriented dialogue systems struggle when a new domain has only a few hundred labeled utterances. Unseen phrasings of familiar requests then cause errors. Earlier LU augmentation (Kurata et al., 2016a) added noise to one utterance at a time and ignored other training examples with the same meaning. Hou et al. instead group training utterances by identical semantic frame and treat members of a group as rewrites of one another. Utterances are first delexicalised, with slot values swapped for slot-type placeholders. A seq2seq model is then trained to map one placeholder sentence to its alternatives. A diversity rank token appended to the input lets the model choose between near-copies and substantially reworded outputs, and the same ranking discards overly similar training pairs. Generated templates are filled back in with slot values chosen to suit the surrounding context. With little data, this clearly improves a BiLSTM tagger on ATIS and on new slot annotations for the Stanford dialogue dataset. The result shows that purely data-driven paraphrasing can enlarge scarce LU data without hand-written domain rules.

## Key points
- **Data:** experiments use ATIS and a newly created slot-filling annotation layer on the Stanford Multi-turn, Multi-domain Dialogue Dataset (three new domains).
- **ATIS results:** with a 129-utterance training subset, slot-filling F-score rises by 6.38 over the baseline; on a medium-sized subset the gain is 2.87.
- **Stanford dialogue dataset results:** the average gain is 10.04 F with 100 training utterances but only 0.47 with 500. Benefits therefore shrink as data grows.
- **Model setup:**
  - Generator: an attention-based input-feeding seq2seq model (Luong et al., 2015), decoded with beam size 10.
  - Surface realisation: slot values are keyed by slot type plus its 5 neighbouring words.
  - LU module: a BiLSTM tagger.
- **Comparison and code:** case studies indicate more varied outputs than Kurata et al. (2016a), whose augmentations largely repeat the source. Code is available at github.com/AtmaHou/Seq2SeqDataAugmentationForLU.

*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

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 76 works · 27,918 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 (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 401 works

## Cite

Cite as: Yutai Hou, Yijia Liu, Wanxiang Che and Ting Liu. 2018. Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding. Proceedings of the 27th International Conference on Computational Linguistics.

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

```bibtex
@inproceedings{hou2018sequence,
  title = {{Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding}},
  author = {Yutai Hou, Yijia Liu, Wanxiang Che and Ting Liu},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  year = {2018},
  url = {https://aclanthology.org/C18-1105/}
}
```

- [← previous Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization](https://md.research.elamur.ai/free/en/papers/dean-2018-resolving-event-coreference-supervised-representation/)
- [next → The First Multilingual Surface Realisation Shared Task (SR'18): Overview and Evaluation Results](https://md.research.elamur.ai/free/en/papers/mille-2018-first-multilingual-surface-realisation-shared/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/4/)

## References

46 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthreas Antoniou, Amos Storkey, and Harrison Edwards. 2018. Data augmentation generative adversarial networks. [find](https://scholar.google.com/scholar?q=Anthreas+Antoniou%2C+Amos+Storkey%2C+and+Harrison+Edwards%2E+2018%2E+Data+augmentation+generative+adversarial+networks%2E)
2. Layla El Asri, Jing He, and Kaheer Suleman. 2016. A sequence-to-sequence model for user simulation in spoken dialogue systems. arXiv preprint arXiv:1607.00070. — [arXiv:1607.00070](https://arxiv.org/abs/1607.00070) [find](https://scholar.google.com/scholar?q=Layla+El+Asri%2C+Jing+He%2C+and+Kaheer+Suleman%2E+2016%2E+A+sequence%2Dto%2Dsequence+model+for+user+simulation+in+spoken+dialogue+systems%2E+arXiv+preprint+arXiv%3A1607%2E00070%2E+%E2%80%94+%5BarXiv%3A1607%2E00070%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
3. Colin Bannard and Chris Callison-Burch. 2005. [Paraphrasing with bilingual parallel corpora](https://md.research.elamur.ai/free/en/papers/bannard-2005-paraphrasing-bilingual-parallel-corpora/). In Proc. of ACL.
4. Regina Barzilay and Kathleen R. McKeown. 2001. [Extracting paraphrases from a parallel corpus](https://md.research.elamur.ai/free/en/papers/barzilay-2001-extracting-paraphrases-parallel-corpus/). In Proc. of ACL.
5. Chris Callison-Burch. 2008. [Syntactic constraints on paraphrases extracted from parallel corpora](https://md.research.elamur.ai/free/en/papers/burch-2008-syntactic-constraints-paraphrases-extracted-parallel/). In Proc. of EMNLP.
6. Yun-Nung Chen, Dilek Hakanni-Tür, Gokhan Tur, Asli Celikyilmaz, Jianfeng Guo, and Li Deng. 2016a. Syntax or semantics? knowledge-guided joint semantic frame parsing. In SLT, pages 348–355. [find](https://scholar.google.com/scholar?q=Yun%2DNung+Chen%2C+Dilek+Hakanni%2DTu%CC%88r%2C+Gokhan+Tur%2C+Asli+Celikyilmaz%2C+Jianfeng+Guo%2C+and+Li+Deng%2E+2016a%2E+Syntax+or+semantics%3F+knowledge%2Dguided+joint+semantic+frame+parsing%2E+In+SLT%2C+pages+348%E2%80%93355%2E)
7. Yun-Nung Vivian Chen, Dilek Hakkani-Tür, Gokhan Tur, Jianfeng Gao, and Li Deng. 2016b. End-to-end memory networks with knowledge carryover for multi-turn spoken language understanding. In INTERSPEECH. [find](https://scholar.google.com/scholar?q=Yun%2DNung+Vivian+Chen%2C+Dilek+Hakkani%2DTu%CC%88r%2C+Gokhan+Tur%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+INTERSPEECH)
8. Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, and Hiroshi Shimodaira. 2005. Human-computer dialogue simulation using hidden markov models. In ASRU, pages 290–295. IEEE. [find](https://scholar.google.com/scholar?q=Heriberto+Cuaya%CC%81huitl%2C+Steve+Renals%2C+Oliver+Lemon%2C+and+Hiroshi+Shimodaira%2E+2005%2E+Human%2Dcomputer+dialogue+simulation+using+hidden+markov+models%2E+In+ASRU%2C+pages+290%E2%80%93295%2E+IEEE%2E)
9. W. Eckert, E. Levin, and R. Pieraccini. [find](https://scholar.google.com/scholar?q=W%2E+Eckert%2C+E%2E+Levin%2C+and+R%2E+Pieraccini%2E)
10. Mihail Eric and Christopher D Manning. 2017. Key-value retrieval networks for task-oriented dialogue. arXiv preprint arXiv:1705.05414. [find](https://scholar.google.com/scholar?q=Mihail+Eric+and+Christopher+D+Manning%2E+2017%2E+Key%2Dvalue+retrieval+networks+for+task%2Doriented+dialogue%2E+arXiv+preprint+arXiv%3A1705%2E05414%2E)
11. Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. 2013. [Paraphrase-driven learning for open question answering](https://md.research.elamur.ai/free/en/papers/fader-2013-paraphrase-driven-learning-open-question/). In Proc. of ACL.
12. Kallirroi Georgila, James Henderson, and Oliver Lemon. 2005. Learning user simulations for information state update dialogue systems. In Ninth European Conference on Speech Communication and Technology. [find](https://scholar.google.com/scholar?q=Kallirroi+Georgila%2C+James+Henderson%2C+and+Oliver+Lemon%2E+2005%2E+Learning+user+simulations+for+information+state+update+dialogue+systems%2E+In+Ninth+European+Conference+on+Speech+Communication+and+Technolog)
13. Kevin Gimpel, Dhruv Batra, Chris Dyer, and Gregory Shakhnarovich. 2013. A systematic exploration of diversity in machine translation. In Proc. of EMNLP. [find](https://scholar.google.com/scholar?q=Kevin+Gimpel%2C+Dhruv+Batra%2C+Chris+Dyer%2C+and+Gregory+Shakhnarovich%2E+2013%2E+A+systematic+exploration+of+diversity+in+machine+translation%2E+In+Proc%2E+of+EMNLP%2E)
14. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, editors, Advances in Neural Information Processing System… [find](https://scholar.google.com/scholar?q=Ian+Goodfellow%2C+Jean+Pouget%2DAbadie%2C+Mehdi+Mirza%2C+Bing+Xu%2C+David+Warde%2DFarley%2C+Sherjil+Ozair%2C+Aaron+Courville%2C+and+Yoshua+Bengio%2E+2014%2E+Generative+adversarial+nets%2E+In+Z%2E+Ghahramani%2C+M%2E+Welling%2C+C%2E+Cor)
15. Awni Y. Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, and Andrew Y. Ng. 2014. [Deep speech: Scaling up end-to-end speech recognition](https://md.research.elamur.ai/free/en/papers/hannun-2014-deep-speech-scaling-up-end/). CoRR, abs/1412.5567.
16. Robin Jia and Percy Liang. 2016. Data recombination for neural semantic parsing. In Proc. of ACL. [find](https://scholar.google.com/scholar?q=Robin+Jia+and+Percy+Liang%2E+2016%2E+Data+recombination+for+neural+semantic+parsing%2E+In+Proc%2E+of+ACL%2E)
17. 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)
18. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander Rush. 2017. [Opennmt: Open-source toolkit for neural machine translation](https://md.research.elamur.ai/free/en/papers/klein-2017-opennmt-open-source-toolkit-neural/). In Proc. of ACL 2017, System Demonstrations.
19. Florian Kreyssig, Inigo Casanueva, Pawel Budzianowski, and Milica Gasic. 2018. Neural user simulation for corpus-based policy optimisation for spoken dialogue systems. arXiv preprint arXiv:1805.06966. — [arXiv:1805.06966](https://arxiv.org/abs/1805.06966) [find](https://scholar.google.com/scholar?q=Florian+Kreyssig%2C+Inigo+Casanueva%2C+Pawel+Budzianowski%2C+and+Milica+Gasic%2E+2018%2E+Neural+user+simulation+for+corpus%2Dbased+policy+optimisation+for+spoken+dialogue+systems%2E+arXiv+preprint+arXiv%3A1805%2E06966%2E)
20. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 25, pages 1097–1105. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Alex+Krizhevsky%2C+Ilya+Sutskever%2C+and+Geoffrey+E+Hinton%2E+2012%2E+Imagenet+classification+with+deep+convolutional+neural+networks%2E+In+F%2E+Pereira%2C+C%2E+J%2E+C%2E+Burges%2C+L%2E+Bottou%2C+and+K%2E+Q%2E+Weinberger%2C+editors%2C)
21. Gakuto Kurata, Bing Xiang, and Bowen Zhou. 2016a. Labeled data generation with encoder-decoder LSTM for semantic slot filling. In INTERSPEECH 2016, pages 725–729. [find](https://scholar.google.com/scholar?q=Gakuto+Kurata%2C+Bing+Xiang%2C+and+Bowen+Zhou%2E+2016a%2E+Labeled+data+generation+with+encoder%2Ddecoder+LSTM+for+semantic+slot+filling%2E+In+INTERSPEECH+2016%2C+pages+725%E2%80%93729%2E)
22. Gakuto Kurata, Bing Xiang, Bowen Zhou, and Mo Yu. 2016b. Leveraging sentence-level information with encoder lstm for semantic slot filling. In Proc. of EMNLP. [find](https://scholar.google.com/scholar?q=Gakuto+Kurata%2C+Bing+Xiang%2C+Bowen+Zhou%2C+and+Mo+Yu%2E+2016b%2E+Leveraging+sentence%2Dlevel+information+with+encoder+lstm+for+semantic+slot+filling%2E+In+Proc%2E+of+EMNLP%2E)
23. Gakuto Kurata, Bing Xiang, Bowen Zhou, and Mo Yu. 2016c. Leveraging sentence-level information with encoder lstm for semantic slot filling. arXiv preprint arXiv:1601.01530. [find](https://scholar.google.com/scholar?q=Gakuto+Kurata%2C+Bing+Xiang%2C+Bowen+Zhou%2C+and+Mo+Yu%2E+2016c%2E+Leveraging+sentence%2Dlevel+information+with+encoder+lstm+for+semantic+slot+filling%2E+arXiv+preprint+arXiv%3A1601%2E01530%2E)
24. Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. [Effective approaches to attention-based neural machine translation](https://md.research.elamur.ai/free/en/papers/luong-2015-effective-approaches-attention-based-neural/). In Proc. of EMNLP.
25. Grégoire Mesnil, Xiaodong He, Li Deng, and Yoshua Bengio. 2013. Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding. In INTERSPEECH 2013. [find](https://scholar.google.com/scholar?q=Gre%CC%81goire+Mesnil%2C+Xiaodong+He%2C+Li+Deng%2C+and+Yoshua+Bengio%2E+2013%2E+Investigation+of+recurrent%2Dneural%2Dnetwork+architectures+and+learning+methods+for+spoken+language+understanding%2E+In+INTERSPEECH+2013%2E)
26. Grégoire Mesnil, Yann Dauphin, Kaisheng Yao, Yoshua Bengio, Li Deng, Dilek Z. Hakkani-Tür, Xiaodong He, Larry P. Heck, Gökhan Tür, Dong Yu, and Geoffrey Zweig. 2015. Using recurrent neural networks for slot filling in spoken language understanding. IEEE/ACM TASLP, 23(3):530–539. [find](https://scholar.google.com/scholar?q=Gre%CC%81goire+Mesnil%2C+Yann+Dauphin%2C+Kaisheng+Yao%2C+Yoshua+Bengio%2C+Li+Deng%2C+Dilek+Z%2E+Hakkani%2DTu%CC%88r%2C+Xiaodong+He%2C+Larry+P%2E+Heck%2C+Go%CC%88khan+Tu%CC%88r%2C+Dong+Yu%2C+and+Geoffrey+Zweig%2E+2015%2E+Using+recurrent+neural+network)
27. Shashi Narayan, Siva Reddy, and Shay B. Cohen. 2016. Paraphrase generation from latent-variable pcfgs for semantic parsing. In Proc. of INLG. [find](https://scholar.google.com/scholar?q=Shashi+Narayan%2C+Siva+Reddy%2C+and+Shay+B%2E+Cohen%2E+2016%2E+Paraphrase+generation+from+latent%2Dvariable+pcfgs+for+semantic+parsing%2E+In+Proc%2E+of+INLG%2E)
28. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In EMNLP, pages 1532–1543.
29. R. Pieraccini, E. Tzoukermann, Z. Gorelov, J. L. Gauvain, E. Levin, C. H. Lee, and J. G. Wilpon. 1992. A speech understanding system based on statistical representation of semantics. In Proc. of ICASSP, Mar. [find](https://scholar.google.com/scholar?q=R%2E+Pieraccini%2C+E%2E+Tzoukermann%2C+Z%2E+Gorelov%2C+J%2E+L%2E+Gauvain%2C+E%2E+Levin%2C+C%2E+H%2E+Lee%2C+and+J%2E+G%2E+Wilpon%2E+1992%2E+A+speech+understanding+system+based+on+statistical+representation+of+semantics%2E+In+Proc%2E+of+ICASS)
30. Olivier Pietquin and Thierry Dutoit. 2006. A probabilistic framework for dialog simulation and optimal strategy learning. IEEE Transactions on Audio, Speech, and Language Processing, 14(2):589–599. [find](https://scholar.google.com/scholar?q=Olivier+Pietquin+and+Thierry+Dutoit%2E+2006%2E+A+probabilistic+framework+for+dialog+simulation+and+optimal+strategy+learning%2E+IEEE+Transactions+on+Audio%2C+Speech%2C+and+Language+Processing%2C+14%282%29%3A589%E2%80%93599%2E)
31. P. J. Price. 1990. Evaluation of spoken language systems: The atis domain. In Proc. of the Workshop on Speech and Natural Language, HLT ’90. [find](https://scholar.google.com/scholar?q=P%2E+J%2E+Price%2E+1990%2E+Evaluation+of+spoken+language+systems%3A+The+atis+domain%2E+In+Proc%2E+of+the+Workshop+on+Speech+and+Natural+Language%2C+HLT+%E2%80%9990%2E)
32. Nils Reimers and Iryna Gurevych. 2017. [Reporting score distributions makes a difference: Performance study of lstm-networks for sequence tagging](https://md.research.elamur.ai/free/en/papers/reimers-2017-reporting-score-distributions-makes-difference/). In Proc. of EMNLP.
33. Kenji Sagae, Maider Lehr, E Prud’hommeaux, Puyang Xu, Nathan Glenn, Damianos Karakos, Sanjeev Khudanpur, Brian Roark, Murat Saraclar, Izhak Shafran, et al. 2012. Hallucinated n-best lists for discriminative language modeling. In ICASSP, pages 5001–5004. IEEE. [find](https://scholar.google.com/scholar?q=Kenji+Sagae%2C+Maider+Lehr%2C+E+Prud%E2%80%99hommeaux%2C+Puyang+Xu%2C+Nathan+Glenn%2C+Damianos+Karakos%2C+Sanjeev+Khudanpur%2C+Brian+Roark%2C+Murat+Saraclar%2C+Izhak+Shafran%2C+et+al%2E+2012%2E+Hallucinated+n%2Dbest+lists+for+discrimi)
34. Jost Schatzmann, Blaise Thomson, Karl Weilhammer, Hui Ye, and Steve Young. 2007a. [Agenda-based user simulation for bootstrapping a pomdp dialogue system](https://md.research.elamur.ai/free/en/papers/schatzmann-2007-agenda-based-user-simulation-bootstrapping/). In NAACL, pages 149–152. Association for Computational Linguistics.
35. Jost Schatzmann, Blaise Thomson, and Steve Young. 2007b. Error simulation for training statistical dialogue systems. In ASRU, pages 526–531. IEEE. [find](https://scholar.google.com/scholar?q=Jost+Schatzmann%2C+Blaise+Thomson%2C+and+Steve+Young%2E+2007b%2E+Error+simulation+for+training+statistical+dialogue+systems%2E+In+ASRU%2C+pages+526%E2%80%93531%2E+IEEE%2E)
36. Konrad Scheffler and Steve Young. 2000. Probabilistic simulation of human-machine dialogues. In ICASSP, volume 2, pages II1217–II1220. IEEE. [find](https://scholar.google.com/scholar?q=Konrad+Scheffler+and+Steve+Young%2E+2000%2E+Probabilistic+simulation+of+human%2Dmachine+dialogues%2E+In+ICASSP%2C+volume+2%2C+pages+II1217%E2%80%93II1220%2E+IEEE%2E)
37. Konrad Scheffler and Steve Young. 2001. Corpus-based dialogue simulation for automatic strategy learning and evaluation. In NAACL, pages 64–70. [find](https://scholar.google.com/scholar?q=Konrad+Scheffler+and+Steve+Young%2E+2001%2E+Corpus%2Dbased+dialogue+simulation+for+automatic+strategy+learning+and+evaluation%2E+In+NAACL%2C+pages+64%E2%80%9370%2E)
38. Rion Snow, Brendan O’Connor, Daniel Jurafsky, and Andrew Y Ng. 2008. [Cheap and fast—but is it good?: evaluating non-expert annotations for natural language tasks](https://md.research.elamur.ai/free/en/papers/snow-2008-cheap-fast-but-is-it/). In Proc. of EMNLP, pages 254–263.
39. Ashwin K. Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David J. Crandall, and Dhruv Batra. 2016. [Diverse beam search: Decoding diverse solutions from neural sequence models](https://md.research.elamur.ai/free/en/papers/vijayakumar-2016-diverse-beam-search-decoding-diverse/). CoRR, abs/1610.02424.
40. William Yang Wang and Diyi Yang. 2015. [That’s so annoying!!!: A lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using\# petpeeve tweets](https://md.research.elamur.ai/free/en/papers/wang-2015-that-s-so-annoying-lexical/). In Proc. of EMNLP, pages 2557–2563.
41. Kaisheng Yao, Geoffrey Zweig, Mei-Yuh Hwang, Yangyang Shi, and Dong Yu. 2013. Recurrent neural networks for language understanding. In Interspeech, pages 2524–2528. [find](https://scholar.google.com/scholar?q=Kaisheng+Yao%2C+Geoffrey+Zweig%2C+Mei%2DYuh+Hwang%2C+Yangyang+Shi%2C+and+Dong+Yu%2E+2013%2E+Recurrent+neural+networks+for+language+understanding%2E+In+Interspeech%2C+pages+2524%E2%80%932528%2E)
42. K. Yao, B. Peng, Y. Zhang, D. Yu, G. Zweig, and Y. Shi. 2014. Spoken language understanding using long short-term memory neural networks. In 2014 IEEE SLT, pages 189–194, Dec. [find](https://scholar.google.com/scholar?q=K%2E+Yao%2C+B%2E+Peng%2C+Y%2E+Zhang%2C+D%2E+Yu%2C+G%2E+Zweig%2C+and+Y%2E+Shi%2E+2014%2E+Spoken+language+understanding+using+long+short%2Dterm+memory+neural+networks%2E+In+2014+IEEE+SLT%2C+pages+189%E2%80%93194%2C+Dec%2E)
43. Steve Young, Milica Gašić, Blaise Thomson, and Jason D Williams. 2013. Pomdp-based statistical spoken dialog systems: A review. Proc. of the IEEE, 101(5):1160–1179. [find](https://scholar.google.com/scholar?q=Steve+Young%2C+Milica+Gas%CC%8Cic%CC%81%2C+Blaise+Thomson%2C+and+Jason+D+Williams%2E+2013%2E+Pomdp%2Dbased+statistical+spoken+dialog+systems%3A+A+review%2E+Proc%2E+of+the+IEEE%2C+101%285%29%3A1160%E2%80%931179%2E)
44. Feifei Zhai, Saloni Potdar, Bing Xiang, and Bowen Zhou. 2017. Neural models for sequence chunking. In AAAI, pages 3365–3371. [find](https://scholar.google.com/scholar?q=Feifei+Zhai%2C+Saloni+Potdar%2C+Bing+Xiang%2C+and+Bowen+Zhou%2E+2017%2E+Neural+models+for+sequence+chunking%2E+In+AAAI%2C+pages+3365%E2%80%933371%2E)
45. Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. [Character-level convolutional networks for text classification](https://md.research.elamur.ai/free/en/papers/zhang-2015-character-level-convolutional-networks-text/). In Advances in neural information processing systems, pages 649–657.
46. Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz. 2018. [mixup: Beyond empirical risk minimization](https://md.research.elamur.ai/free/en/papers/zhang-2017-mixup-empirical-risk-minimization/). In International Conference on Learning Representations.

*Updated 24 October 2026*