Efficient Natural Language Response Suggestion for Smart Reply

This paper presents a computationally efficient machine-learned method for natural language response suggestion. Feed-forward neural networks using n-gram embedding features encode messages into vectors which are optimized to give message-response pairs a high dot-product value. An optimized search finds response suggestions. The method is evaluated in a large-scale commercial e-mail application, Inbox by Gmail. Compared to a sequence-to-sequence approach, the new system achieves the same quality at a small fraction of the computational requirements and latency.

[1]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[2]  P. J. Price,et al.  Evaluation of Spoken Language Systems: the ATIS Domain , 1990, HLT.

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Steve J. Young,et al.  Talking to machines (statistically speaking) , 2002, INTERSPEECH.

[5]  Cordelia Schmid,et al.  Product Quantization for Nearest Neighbor Search , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  R. Kurzweil.  How to Create a Mind: The Secret of Human Thought Revealed , 2012 .

[7]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[8]  David J. Fleet,et al.  Cartesian K-Means , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[10]  Geoffrey Zweig,et al.  Recurrent neural networks for language understanding , 2013, INTERSPEECH.

[11]  Larry P. Heck,et al.  Learning deep structured semantic models for web search using clickthrough data , 2013, CIKM.

[12]  Ping Li,et al.  Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) , 2014, NIPS.

[13]  Matthew Henderson,et al.  Word-Based Dialog State Tracking with Recurrent Neural Networks , 2014, SIGDIAL Conference.

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

[15]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[16]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[17]  Geoffrey Zweig,et al.  Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[18]  Geoffrey E. Hinton,et al.  Grammar as a Foreign Language , 2014, NIPS.

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

[20]  Pascal Vincent,et al.  Clustering is Efficient for Approximate Maximum Inner Product Search , 2015, ArXiv.

[21]  Jimmy J. Lin,et al.  Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks , 2015, EMNLP.

[22]  Wei Liu,et al.  Learning Binary Codes for Maximum Inner Product Search , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[24]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[25]  Geoffrey Zweig,et al.  End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning , 2016, ArXiv.

[26]  Bowen Zhou,et al.  ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs , 2015, TACL.

[27]  Javier Snaider,et al.  Conversational Contextual Cues: The Case of Personalization and History for Response Ranking , 2016, ArXiv.

[28]  Peter Young,et al.  Smart Reply: Automated Response Suggestion for Email , 2016, KDD.

[29]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[30]  Sanjiv Kumar,et al.  Quantization based Fast Inner Product Search , 2015, AISTATS.

[31]  Noam Shazeer,et al.  Swivel: Improving Embeddings by Noticing What's Missing , 2016, ArXiv.

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