Wizard of Wikipedia: Knowledge-Powered Conversational agents

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.

[1]  Mitesh M. Khapra,et al.  Towards Exploiting Background Knowledge for Building Conversation Systems , 2018, EMNLP.

[2]  Joelle Pineau,et al.  Extending Neural Generative Conversational Model using External Knowledge Sources , 2018, EMNLP.

[3]  Antoine Bordes,et al.  Training Millions of Personalized Dialogue Agents , 2018, EMNLP.

[4]  Eunsol Choi,et al.  QuAC: Question Answering in Context , 2018, EMNLP.

[5]  Xiaoyan Zhu,et al.  Commonsense Knowledge Aware Conversation Generation with Graph Attention , 2018, IJCAI.

[6]  Nan Hua,et al.  Universal Sentence Encoder , 2018, ArXiv.

[7]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[8]  Angela Fan,et al.  Controllable Abstractive Summarization , 2017, NMT@ACL.

[9]  Jason Weston,et al.  StarSpace: Embed All The Things! , 2017, AAAI.

[10]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[11]  Matthew Henderson,et al.  Efficient Natural Language Response Suggestion for Smart Reply , 2017, ArXiv.

[12]  Jason Weston,et al.  Reading Wikipedia to Answer Open-Domain Questions , 2017, ACL.

[13]  Hannes Schulz,et al.  Frames: a corpus for adding memory to goal-oriented dialogue systems , 2017, SIGDIAL Conference.

[14]  Ming-Wei Chang,et al.  A Knowledge-Grounded Neural Conversation Model , 2017, AAAI.

[15]  Daniel Jurafsky,et al.  A Simple, Fast Diverse Decoding Algorithm for Neural Generation , 2016, ArXiv.

[16]  Joelle Pineau,et al.  Generative Deep Neural Networks for Dialogue: A Short Review , 2016, ArXiv.

[17]  Ashwin K. Vijayakumar,et al.  Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models , 2016, ArXiv.

[18]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[19]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[20]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[21]  Xiang Zhang,et al.  Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems , 2015, ICLR.

[22]  Alexandra Birch,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[23]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

[24]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[25]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[26]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[27]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[28]  Niels Ole Bernsen,et al.  Designing interactive speech systems - from first ideas to user testing , 1998 .