---
title: "An End-to-end Approach for Handling Unknown Slot Values in"
description: "Most dialogue state trackers assume a fixed ontology that lists every value a slot can take. 29 references, cited by 49 papers here."
authors: ["Puyang Xu", "Qi Hu"]
year: 2018
venue: "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P18-1134/"
doi: "10.18653/v1/p18-1134"
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/xu-2018-end-end-approach-handling-unknown/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2018-end-end-approach-handling-unknown/)

[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/3/) / An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking

# An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking

**Authors:** Puyang Xu and Qi Hu · **Year:** 2018 · **Venue:** [Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2018](https://md.research.elamur.ai/free/en/venues/acl/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/P18-1134/) · [PDF](https://aclanthology.org/P18-1134.pdf) · [DOI 10.18653/v1/p18-1134](https://doi.org/10.18653/v1/p18-1134) · [OpenAlex](https://openalex.org/W2963283951)

**Citations:** 137 citations (OpenAlex, 2026-10-14) · [49](https://md.research.elamur.ai/free/en/papers/xu-2018-end-end-approach-handling-unknown/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Most dialogue state trackers assume a fixed ontology that lists every value a slot can take. In industrial settings this list is often unavailable, very large, or constantly changing. End-to-end trackers that work without an SLU module therefore cannot output values they have never been told about. Xu and Hu address this by treating state tracking as span extraction. A pointer network (PtrNet) with a bidirectional LSTM encoder reads the dialogue history, enriched with speaker-role and entity-type features. Its decoder then points to the start and end positions of the slot value in the text. A jointly trained classifier covers values that cannot be pointed to, such as none or dontcare. A targeted feature dropout during training helps the model generalize to values absent from training. On DSTC2 the system reaches near state-of-the-art joint goal accuracy using only 1-best ASR and no SLU. On modified DSTC2 and bAbI data, the dropout greatly improves recognition of unknown values. This matters for real deployments where back-end databases are only reachable through external APIs.

## Key points
- The hybrid model reaches 72.1% joint goal accuracy on the DSTC2 test set, compared with 74.0 for MemN2N, 73.4 for NBT-CNN and 70.3 for the SLU-dependent Scalable Multi-domain DST.
- On DSTC2 the classifier makes a three-way decision (none / dontcare / other). Other non-pointable values, mostly caused by ASR errors, limit the achievable accuracy: in the test data, their share is 9.7% for food, 7.6% for location and 4.7% for price.
- On a modified DSTC2 setup with a reduced training set, a 5% targeted dropout raised accuracy on unknown food types from 11.6% to 34.4%. Accuracy on known values stayed about the same.
- On bAbI Task 5 OOV API calls, dropout with p=0.1 raised food accuracy from 86.2 to 100 and location accuracy from 74.7 to 99.6. This fully closed the gap with the regular test set.

*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 Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 263 works · 180,581 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 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: Puyang Xu and Qi Hu. 2018. An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{xu2018end,
  title = {{An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking}},
  author = {Puyang Xu and Qi Hu},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1134},
  url = {https://doi.org/10.18653/v1/p18-1134}
}
```

- [← previous On the Impact of Various Types of Noise on Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/khayrallah-2018-impact-various-types-noise-neural/)
- [next → Guiding Neural Machine Translation with Retrieved Translation Pieces](https://md.research.elamur.ai/free/en/papers/zhang-2018-guiding-neural-machine-translation-retrieved/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/)

## References

29 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Antoine Bordes and Jason Weston. 2016. Learning end-to-end goal-oriented dialog. In CoRR. [find](https://scholar.google.com/scholar?q=Antoine+Bordes+and+Jason+Weston%2E+2016%2E+Learning+end%2Dto%2Dend+goal%2Doriented+dialog%2E+In+CoRR%2E)
2. Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Chen Yun-Nung, Faisal Ahmed, and Deng Li. 2017. [Towards end-to-end reinforcement learning of dialogue agents for information access](https://md.research.elamur.ai/free/en/papers/dhingra-2017-end-end-reinforcement-learning-dialogue/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL).
3. Mihail Eric and Christopher Manning. 2017a. A copy-augmented sequence-to-sequence architecture gives good performance on task-oriented dialogue. In arXiv preprint arXiv:1701.04024v3 [cs.CL]. [find](https://scholar.google.com/scholar?q=Mihail+Eric+and+Christopher+Manning%2E+2017a%2E+A+copy%2Daugmented+sequence%2Dto%2Dsequence+architecture+gives+good+performance+on+task%2Doriented+dialogue%2E+In+arXiv+preprint+arXiv%3A1701%2E04024v3+%5Bcs%2ECL%5D%2E)
4. Mihail Eric and Christopher Manning. 2017b. Key-value retrieval networks for task-oriented dialogue. In arXiv preprint arXiv:1705.05414v2 [cs.CL]. [find](https://scholar.google.com/scholar?q=Mihail+Eric+and+Christopher+Manning%2E+2017b%2E+Key%2Dvalue+retrieval+networks+for+task%2Doriented+dialogue%2E+In+arXiv+preprint+arXiv%3A1705%2E05414v2+%5Bcs%2ECL%5D%2E)
5. Jiatao Gu, Zhengdong Lu, Hang Li, and Victor Li. 2016. [Incorporating copying mechanism in sequence-to-sequence learning](https://md.research.elamur.ai/free/en/papers/gu-2016-incorporating-copying-mechanism-sequence-sequence/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL).
6. Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. 2016. [Pointing the unknown words](https://md.research.elamur.ai/free/en/papers/gulcehre-2016-pointing-unknown-words/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL).
7. Matthew Henderson, Blaise Thomson, and Jason Williams. 2014a. The second dialog state tracking challenge. In 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue. [find](https://scholar.google.com/scholar?q=Matthew+Henderson%2C+Blaise+Thomson%2C+and+Jason+Williams%2E+2014a%2E+The+second+dialog+state+tracking+challenge%2E+In+15th+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+and+Dialogue%2E)
8. Matthew Henderson, Blaise Thomson, and Steve Young. 2014b. Robust dialosg state tracking using delexicalised recurrent neural networks and unsupervised adaptation. In Proceedings of IEEE Spoken Language Technology.. [find](https://scholar.google.com/scholar?q=Matthew+Henderson%2C+Blaise+Thomson%2C+and+Steve+Young%2E+2014b%2E+Robust+dialosg+state+tracking+using+delexicalised+recurrent+neural+networks+and+unsupervised+adaptation%2E+In+Proceedings+of+IEEE+Spoken+Langua)
9. Matthew Henderson, Blaise Thomson, and Steve Young. 2014c. [Word based dialog state tracking with recurrent neural networks](https://md.research.elamur.ai/free/en/papers/henderson-2014-word-based-dialog-state-tracking/). In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL).
10. Geoffrey Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2012. Improving neural networks by preventing co-adaptation of feature detectors. In arXiv preprint arXiv:1207.0580v1 [cs.NE]. [find](https://scholar.google.com/scholar?q=Geoffrey+Hinton%2C+Nitish+Srivastava%2C+Alex+Krizhevsky%2C+Ilya+Sutskever%2C+and+Ruslan+Salakhutdinov%2E+2012%2E+Improving+neural+networks+by+preventing+co%2Dadaptation+of+feature+detectors%2E+In+arXiv+preprint+arXiv)
11. Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Diederik+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+Proceedings+of+the+3rd+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
12. Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz. 2017. [End-to-end task-completion neural dialogue systems](https://md.research.elamur.ai/free/en/papers/li-2017-end-end-task-completion-neural/). In arxiv preprint arXiv:1703.01008v3 [cs.CL].
13. Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, and Larry Heck. 2017. End-to-end optimization of task-oriented dialogue model with deep reinforcement learning. In arxiv preprint arXiv:1711.10712v2 [cs.CL]. — [arXiv:1711.10712](https://arxiv.org/abs/1711.10712) [find](https://scholar.google.com/scholar?q=Bing+Liu%2C+Gokhan+Tur%2C+Dilek+Hakkani%2DTur%2C+Pararth+Shah%2C+and+Larry+Heck%2E+2017%2E+End%2Dto%2Dend+optimization+of+task%2Doriented+dialogue+model+with+deep+reinforcement+learning%2E+In+arxiv+preprint+arXiv%3A1711%2E1071)
14. Metallinou Metallinou, Dan Bohus, and Jason Williams. 2013. Discriminative state tracking for spoken dialog systems. In Proceedings of the 51th Annual Meeting of the Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Metallinou+Metallinou%2C+Dan+Bohus%2C+and+Jason+Williams%2E+2013%2E+Discriminative+state+tracking+for+spoken+dialog+systems%2E+In+Proceedings+of+the+51th+Annual+Meeting+of+the+Association+for+Computational+Ling)
15. Nikola Mrksic, Diarmuid Seaghdha, Blaise Thomson, Milica Gasic, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2015. Multi-domain dialog state tracking using recurrent neural networks. In Proceedings of the 53th Annual Meeting of the Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Nikola+Mrksic%2C+Diarmuid+Seaghdha%2C+Blaise+Thomson%2C+Milica+Gasic%2C+Pei%2DHao+Su%2C+David+Vandyke%2C+Tsung%2DHsien+Wen%2C+and+Steve+Young%2E+2015%2E+Multi%2Ddomain+dialog+state+tracking+using+recurrent+neural+networks%2E+I)
16. Nikola Mrksic, Diarmuid Seaghdha, Tsung-Hsien Wen, Blaise Thomson, and Steve Young. 2017. Neural belief tracker: Data-driven dialogue state tracking. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Nikola+Mrksic%2C+Diarmuid+Seaghdha%2C+Tsung%2DHsien+Wen%2C+Blaise+Thomson%2C+and+Steve+Young%2E+2017%2E+Neural+belief+tracker%3A+Data%2Ddriven+dialogue+state+tracking%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+A)
17. Julien Perez and Fei Liu. 2017. Dialog state tracking, a machine reading approach using memory network. In Proceedings of EACL. [find](https://scholar.google.com/scholar?q=Julien+Perez+and+Fei+Liu%2E+2017%2E+Dialog+state+tracking%2C+a+machine+reading+approach+using+memory+network%2E+In+Proceedings+of+EACL%2E)
18. Abhinav Rastogi, Dilek Hakkani-Tur, and Larry Heck. 2018. Scalable multi-domain dialogue state tracking. In arXiv preprint arXiv:1712.10224v2 [cs.CL]. — [arXiv:1712.10224](https://arxiv.org/abs/1712.10224) [find](https://scholar.google.com/scholar?q=Abhinav+Rastogi%2C+Dilek+Hakkani%2DTur%2C+and+Larry+Heck%2E+2018%2E+Scalable+multi%2Ddomain+dialogue+state+tracking%2E+In+arXiv+preprint+arXiv%3A1712%2E10224v2+%5Bcs%2ECL%5D%2E+%E2%80%94+%5BarXiv%3A1712%2E10224%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1712%2E1)
19. Abigail See, Peter Liu, and Christopher Manning. 2017. Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Abigail+See%2C+Peter+Liu%2C+and+Christopher+Manning%2E+2017%2E+Get+to+the+point%3A+Summarization+with+pointer%2Dgenerator+networks%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+L)
20. Gokhan Tur and Renato De Mori. 2011. Spoken Language Understanding: Systems for Extracting Semantic Information from Speech. Wiley. [find](https://scholar.google.com/scholar?q=Gokhan+Tur+and+Renato+De+Mori%2E+2011%2E+Spoken+Language+Understanding%3A+Systems+for+Extracting+Semantic+Information+from+Speech%2E+Wiley%2E)
21. Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In NIPS. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Meire+Fortunato%2C+and+Navdeep+Jaitly%2E+2015%2E+Pointer+networks%2E+In+NIPS%2E)
22. Shuohang Wang and Jing Jiang. 2016. [Machine comprehension using match-lstm and answer pointer](https://md.research.elamur.ai/free/en/papers/wang-2016-machine-comprehension-using-match-lstm/). In arXiv preprint arXiv:1608.07905v2 [cs.CL].
23. Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017. A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of EACL. [find](https://scholar.google.com/scholar?q=Tsung%2DHsien+Wen%2C+David+Vandyke%2C+Nikola+Mrksic%2C+Milica+Gasic%2C+Lina+M%2E+Rojas%2DBarahona%2C+Pei%2DHao+Su%2C+Stefan+Ultes%2C+and+Steve+Young%2E+2017%2E+A+network%2Dbased+end%2Dto%2Dend+trainable+task%2Doriented+dialogue+system)
24. Jason Weston, Sumit Chopra, and Antoine Bordes. 2014. Memory networks. In CoRR. [find](https://scholar.google.com/scholar?q=Jason+Weston%2C+Sumit+Chopra%2C+and+Antoine+Bordes%2E+2014%2E+Memory+networks%2E+In+CoRR%2E)
25. Jason Williams, Antoine Raux, Deepak Ramachandran, and Alan Black. 2013. The dialog state tracking challenge. In Proceedings of the SIGDIAL 2013 Conference. [find](https://scholar.google.com/scholar?q=Jason+Williams%2C+Antoine+Raux%2C+Deepak+Ramachandran%2C+and+Alan+Black%2E+2013%2E+The+dialog+state+tracking+challenge%2E+In+Proceedings+of+the+SIGDIAL+2013+Conference%2E)
26. Jason Williams and Geoffrey Zweig. 2016. End-to-end lstm-based dialog control optimized with supervised and reinforcement learning. In arxiv preprint arXiv:1606.01269v1 [cs.CL]. — [arXiv:1606.01269](https://arxiv.org/abs/1606.01269) [find](https://scholar.google.com/scholar?q=Jason+Williams+and+Geoffrey+Zweig%2E+2016%2E+End%2Dto%2Dend+lstm%2Dbased+dialog+control+optimized+with+supervised+and+reinforcement+learning%2E+In+arxiv+preprint+arXiv%3A1606%2E01269v1+%5Bcs%2ECL%5D%2E+%E2%80%94+%5BarXiv%3A1606%2E01269%5D%28h)
27. Puyang Xu and Ruhi Sarikaya. 2014. Targeted feature dropout for robust slot filling in natural language understanding. In ISCA - International Speech Communication Association. [find](https://scholar.google.com/scholar?q=Puyang+Xu+and+Ruhi+Sarikaya%2E+2014%2E+Targeted+feature+dropout+for+robust+slot+filling+in+natural+language+understanding%2E+In+ISCA+%2D+International+Speech+Communication+Association%2E)
28. Tiancheng Zhao and Maxine Eskenazi. 2016. Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning. In Proceedings of SIGDIAL 2016 Conference. [find](https://scholar.google.com/scholar?q=Tiancheng+Zhao+and+Maxine+Eskenazi%2E+2016%2E+Towards+end%2Dto%2Dend+learning+for+dialog+state+tracking+and+management+using+deep+reinforcement+learning%2E+In+Proceedings+of+SIGDIAL+2016+Conference%2E)
29. Lukas Zilka and Filip Jurcicek. 2015. Incremental lstm-based dialog state tracker. In ASRU. [find](https://scholar.google.com/scholar?q=Lukas+Zilka+and+Filip+Jurcicek%2E+2015%2E+Incremental+lstm%2Dbased+dialog+state+tracker%2E+In+ASRU%2E)

*Updated 24 October 2026*