2018

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

Xu, Puyang, Hu, Qi

Understand

We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values.

Previous approaches generally assume predefined candidate lists and thus are not designed to output unknown values, especially when the spoken language understanding (SLU) module is absent as in many end-to-end (E2E) systems.
We describe in this paper an E2E architecture based on the pointer network (PtrNet) that can effectively extract unknown slot values while still obtains state-of-the-art accuracy on the standard DSTC2 benchmark.
We also provide extensive empirical evidence to show that tracking unknown values can be challenging and our approach can bring significant improvement with the help of an effective feature dropout technique.

Built on

Spoken Language Understanding: Systems for Extracting Semantic Information from Speech
Gokhan Tur and Renato De Mori. 2011 · 2011
Earlier work this paper cites.
Improving neural networks by preventing co-adaptation of feature detectors
Original
Geoffrey Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2012 · 2012
Earlier work this paper cites.
Discriminative state tracking for spoken dialog systems
Metallinou Metallinou, Dan Bohus, and Jason Williams. 2013 · 2013
Earlier work this paper cites.
The dialog state tracking challenge
Jason Williams, Antoine Raux, Deepak Ramachandran, and Alan Black. 2013 · 2013
Earlier work this paper cites.
Adam: A method for stochastic optimization
Diederik Kingma and Jimmy Ba. 2014 · 2014
Earlier work this paper cites.
Memory networks
Jason Weston, Sumit Chopra, and Antoine Bordes. 2014 · 2014
Earlier work this paper cites.
Targeted feature dropout for robust slot filling in natural language understanding
Puyang Xu and Ruhi Sarikaya. 2014 · 2014
Earlier work this paper cites.
Multi-domain dialog state tracking using recurrent neural networks
Nikola Mrksic, Diarmuid Seaghdha, Blaise Thomson, Milica Gasic, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2015 · 2015
Earlier work this paper cites.

Similar

Pointer networks
Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015 · 2015
Cited alongside, same era.
Incremental lstm-based dialog state tracker
Lukas Zilka and Filip Jurcicek. 2015 · 2015
Cited alongside, same era.
Learning end-to-end goal-oriented dialog
Antoine Bordes and Jason Weston. 2016 · 2016
Cited alongside, same era.
Incorporating copying mechanism in sequence-to-sequence learning
Jiatao Gu, Zhengdong Lu, Hang Li, and Victor Li. 2016 · 2016
Cited alongside, same era.
Pointing the unknown words
Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. 2016 · 2016
Cited alongside, same era.
Machine comprehension using match-lstm and answer pointer
Original
Shuohang Wang and Jing Jiang. 2016 · 2016
Cited alongside, same era.
End-to-end lstm-based dialog control optimized with supervised and reinforcement learning
Original
Jason Williams and Geoffrey Zweig. 2016 · 2016
Cited alongside, same era.
Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning
Tiancheng Zhao and Maxine Eskenazi. 2016 · 2016
Cited alongside, same era.
A copy-augmented sequence-to-sequence architecture gives good performance on task-oriented dialogue
Original
Mihail Eric and Christopher Manning. 2017a
Cited in the paper.
Key-value retrieval networks for task-oriented dialogue
Original
Mihail Eric and Christopher Manning. 2017b
Cited in the paper.
The second dialog state tracking challenge
Matthew Henderson, Blaise Thomson, and Jason Williams. 2014a
Cited in the paper.
Robust dialosg state tracking using delexicalised recurrent neural networks and unsupervised adaptation
Matthew Henderson, Blaise Thomson, and Steve Young. 2014b
Cited in the paper.

Then

Towards end-to-end reinforcement learning of dialogue agents for information access
Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Chen Yun-Nung, Faisal Ahmed, and Deng Li. 2017 · 2017
Later among the works it cites.
End-to-end task-completion neural dialogue systems
Original
Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz. 2017 · 2017
Later among the works it cites.
End-to-end optimization of task-oriented dialogue model with deep reinforcement learning
Original
Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, and Larry Heck. 2017 · 2017
Later among the works it cites.
Neural belief tracker: Data-driven dialogue state tracking
Nikola Mrksic, Diarmuid Seaghdha, Tsung-Hsien Wen, Blaise Thomson, and Steve Young. 2017 · 2017
Later among the works it cites.
Dialog state tracking, a machine reading approach using memory network
Julien Perez and Fei Liu. 2017 · 2017
Later among the works it cites.
Get to the point: Summarization with pointer-generator networks
Abigail See, Peter Liu, and Christopher Manning. 2017 · 2017
Later among the works it cites.
A network-based end-to-end trainable task-oriented dialogue system
Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017 · 2017
Later among the works it cites.
Scalable multi-domain dialogue state tracking
Original
Abhinav Rastogi, Dilek Hakkani-Tur, and Larry Heck. 2018 · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…