Papperoni

2019

Wizard of Wikipedia: Knowledge-Powered Conversational Agents

E. Dinan, S. Roller, K. Shuster, A. Fan, Michael Auli, Jason Weston

Open PDF Google Scholar

citations

Cite Score

39

AI summary

This paper introduces Transformer Memory Networks to build dialogue agents with access to large memory systems, and collect the Wizard of Wikipedia dataset, a large collection of open-domain dialogues grounded by Wikipedia knowledge, demonstrating the effectiveness of models in automatic and human experiments.

Main Contributions

Introduces Transformer Memory Networks, which are capable of retrieving and attending to knowledge and outputting a response in retrieval or generative modes.
Collects the Wizard of Wikipedia dataset, a large collection of open-domain dialogues grounded by Wikipedia knowledge.
Demonstrates the effectiveness of the models in automatic and human experiments.
Shows that models can conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations.
Releases a new benchmark that allows for measuring further improvements in this important research direction.

Abstract

In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popular sequence to sequence models typically “generate and hope” generic utterances that can be memorized in the weights of the model when mapping from input utterance(s) to output, rather than employing recalled knowledge as context. Use of knowledge has so far proved difficult, in part because of the lack of a supervised learning benchmark task which exhibits knowledgeable open dialogue with clear grounding. To that end we collect and release a large dataset with conversations directly grounded with knowledge retrieved from Wikipedia. We then design architectures capable of retrieving knowledge, reading and conditioning on it, and finally generating natural responses. Our best performing dialogue models are able to conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations, while our new benchmark allows for measuring further improvements in this important research direction.

Citation Graph

Loading graph...

References [28]

Sort:

Filter:

[1]Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin - 2017

47 papers in library cite

I mean... it introduced Transformers!

[2]Sequence to Sequence Learning With Neural Networks

Ilya Sutskever, Oriol Vinyals, Quoc V. Le - 2014

58 papers in library cite

Good paper, but I think it only got famous because they set a new good baseline for NNs in MT. Their main contribution was reversing the source sentence TBH.

[3]SQuAD: 100,000+ Questions for Machine Comprehension of Text

P. Rajpurkar, J. Zhang, K. Lopyrev, Percy Liang - 2016

37 papers in library cite

Nice paper that introduced an important dataset. Not much else though.

[4]Neural Machine Translation of Rare Words with Subword Units

R. Sennrich, B. Haddow, Alexandra Birch - 2016

22 papers in library cite

Very good! Simple, explains quite a lot and good results. Forms the basis for a lot of stuff now!

[5]End-to-End Memory Networks

S. Sukhbaatar, A. Szlam, Jason Weston, Rob Fergus - 2015

18 papers in library cite

This was so surprising! This is very similar to transformers and RAG. Who knew?!

[6]A Neural Conversational Model

Oriol Vinyals, Quoc V. Le - 2015

7 papers in library cite

No new methodology, no measurements, no results. It should be like 4 pages long if they didn't fill in with the conversation logs.

[7]Training Millions of Personalized Dialogue Agents

Antoine Bordes - 2018

1 paper in library cites

I think this is very derivative from other papers (which I haven't read yet). But overall is a good read.

[8]Reading Wikipedia to Answer Open-Domain Questions

Deli Chen, Adam Fisch, Jason Weston, Antoine Bordes - 2017

10 papers in library cite

Open Domain QA with wikipedia

[9]Personalizing Dialogue Agents: I Have a Dog, Do You Have Pets Too?

S. Zhang, E. Dinan, J. Urbanek, A. Szlam, Douwe Kiela, Jason Weston - 2018

4 papers in library cite

Maybe the first time I have seen "agents" in a title

[10]Universal Sentence Encoder

D. Cer, Yining Yang, S. Y. Kong, N. Hua, N. Limtiaco, R. S. John, Noah Constant, M. G. Cespedes, S. Yuan, C. Tar, Y. H. Sung, B. Strope, R. Kurzweil - 2018

2 papers in library cite

[11]A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

A. Sordoni, M. Galley, Michael Auli, Chris Brockett, Yangfeng Ji, M. Mitchell, J. Y. Nie, Jianfeng Gao, B. Dolan - 2015

4 papers in library cite

Generating conversational responses

[12]Quac: Question Answering in Context

E. Choi, He He, M. Iyyer, M. Yatskar, W. T. Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer - 2018

8 papers in library cite

[13]A Knowledge-Grounded Neural Conversation Model

M. Ghazvininejad, Chris Brockett, M. W. Chang, B. Dolan, Jianfeng Gao, W. T. Yih, M. Galley - 2017

3 papers in library cite

[14]Efficient Natural Language Response Suggestion for Smart Reply

M. Henderson, R. A. Rfou, B. Strope, Y. H. Sung, L. Lukacs, R. Guo, S. Kumar, B. Miklos, R. Kurzweil - 2017

2 papers in library cite

Embedding customization? I thought this would be more cited

[15]Controllable Abstractive Summarization

A. Fan, D. Grangier, Michael Auli - 2017

2 papers in library cite

[16]Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems

J. Dodge, A. Gane, X. Zhang, Antoine Bordes, S. Chopra, A. Miller, A. Szlam, Jason Weston - 2015

4 papers in library cite

I like these "prerequisite" papers

[17]A Network-Based End-to-End Trainable Task-Oriented Dialogue System

T. H. Wen, D. Vandyke, N. Mrksic, M. Gasic, L. M. R. Barahona, P. H. Su, S. Ultes, S. Young - 2016

3 papers in library cite

[18]Diverse Beam Search: Decoding Diverse Solutions From Neural Sequence Models

A. K. Vijayakumar, M. Cogswell, R. R. Selvaraju, Q. Sun, S. Lee, D. J. Crandall, D. Batra - 2016

2 papers in library cite

[19]Generative Deep Neural Networks for Dialogue: A Short Review

I. V. Serban, Ryan Lowe, L. C. Lin, J. Pineau - 2016

2 papers in library cite

[20]Learning End-to-End Goal-Oriented Dialog

Antoine Bordes, Y. Lan Boureau, Jason Weston - 2016

2 papers in library cite

[21]Towards Exploiting Background Knowledge for Building Conversation Systems

N. Moghe, S. Arora, S. Banerjee, M. M. Khapra - 2018

2 papers in library cite

[22]A Simple, Fast Diverse Decoding algorithm for Neural Generation

Jeffrey Li, W. Monroe, Dan Jurafsky - 2016

1 paper in library cites

[23]Commonsense Knowledge Aware Conversation Generation With Graph Attention

H. Zhou, T. Young, M. Huang, H. Zhao, Jiacheng Xu, X. Zhu - 2018

1 paper in library cites

[24]Designing Interactive Speech Systems: From First Ideas to User Testing

N. O. Bernsen, H. Dybkjaer, L. Dybkjaer - 2012

1 paper in library cites

[25]Extending Neural Generative Conversational Model Using External Knowledge Sources

P. Parthasarathi, J. Pineau - 2018

1 paper in library cites

[26]Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems

L. E. Asri, H. Schulz, S. S. Sharma, J. Zumer, J. Harris, E. Fine, R. Mehrotra, K. Suleman - 2017

1 paper in library cites

[27]Starspace: Embed All the Things!

L. Wu, Adam Fisch, S. Chopra, K. Adams, Antoine Bordes, Jason Weston - 2017

1 paper in library cites

[28]The Second Dialog State Tracking Challenge

M. Henderson, B. Thomson, J. D. Williams - 2014

1 paper in library cites

Cited by

4

papers in your library

Cites

16

papers in your library

Read

on November 13, 2025

This could be the original RAG. It's soooo close to the original thing!

Tags

Paper Aliases

No aliases