English

Efficient Natural Language Response Suggestion for Smart Reply

Computation and Language 2017-05-03 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1705.00652,
  title  = {Efficient Natural Language Response Suggestion for Smart Reply},
  author = {Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
  journal= {arXiv preprint arXiv:1705.00652},
  year   = {2017}
}
R2 v1 2026-06-22T19:33:06.235Z