Fetching the paper…

Reading the bibliography…

2018

Retrieve and Refine: Improved Sequence Generation Models For Dialogue

Weston, Jason, Dinan, Emily, Miller, Alexander H.

Original
PDF
Post on X

Understand

Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging.

Retrieval models on the other hand can surface interesting responses, but are restricted to the given retrieval set leading to erroneous replies that cannot be tuned to the specific context.
In this work we develop a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it -- the final sequence generator treating the retrieval as additional context.
We show on the recent CONVAI2 challenge task our approach produces responses superior to both standard retrieval and generation models in human evaluations.

Retrieve and Refine: Improved Sequence Generation Models For Dialogue · Around

Built on

An information retrieval approach to short text conversation
Original
Zongcheng Ji, Zhengdong Lu, and Hang Li. 2014 · 2014
Earlier work this paper cites.
Sequence to sequence learning with neural networks
Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014 · 2014
Earlier work this paper cites.
How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation
Original
Chia-Wei Liu, Ryan Lowe, Iulian V Serban, Michael Noseworthy, Laurent Charlin, and Joelle Pineau. 2016 · 2016
Earlier work this paper cites.
Key-value memory networks for directly reading documents
Original
Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016 · 2016
Earlier work this paper cites.
Pre-translation for neural machine translation
Original
Jan Niehues, Eunah Cho, Thanh-Le Ha, and Alex Waibel. 2016 · 2016
Earlier work this paper cites.
Iterative refinement for machine translation
Original
Roman Novak, Michael Auli, and David Grangier. 2016 · 2016
Earlier work this paper cites.

Similar

Generative deep neural networks for dialogue: A short review
Original
Iulian Vlad Serban, Ryan Lowe, Laurent Charlin, and Joelle Pineau. 2016 · 2016
Cited alongside, same era.
Controllable abstractive summarization
Original
Angela Fan, David Grangier, and Michael Auli. 2017 · 2017
Cited alongside, same era.
Quickedit: Editing text & translations via simple delete actions
Original
David Grangier and Michael Auli. 2017 · 2017
Cited alongside, same era.
Search engine guided non-parametric neural machine translation
Original
Jiatao Gu, Yong Wang, Kyunghyun Cho, and Victor OK Li. 2017 · 2017
Cited alongside, same era.
Generating sentences by editing prototypes

Then

Adapting sequence models for sentence correction
Original
Allen Schmaltz, Yoon Kim, Alexander M Rush, and Stuart M Shieber. 2017 · 2017
Later among the works it cites.
Deliberation networks: Sequence generation beyond one-pass decoding
Yingce Xia, Fei Tian, Lijun Wu, Jianxin Lin, Tao Qin, Nenghai Yu, and Tie-Yan Liu. 2017 · 2017
Later among the works it cites.
Retrieve, rerank and rewrite: Soft template based neural summarization
Ziqiang Cao, Wenjie Li, Sujian Li, and Furu Wei. 2018 · 2018
Closest in time.
Exemplar encoder-decoder for neural conversation generation
Gaurav Pandey, Danish Contractor, Vineet Kumar, and Sachindra Joshi. 2018 · 2018
Closest in time.
Personalizing dialogue agents: I have a dog, do you have pets too?
Original
Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 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…

Kelvin Guu, Tatsunori B Hashimoto, Yonatan Oren, and Percy Liang. 2017 · 2017

Cited alongside, same era.

An exploration of neural sequence-to-sequence architectures for automatic post-editing

Marcin Junczys-Dowmunt and Roman Grundkiewicz. 2017 · 2017

Cited alongside, same era.