CoChat

Gmail Smart Compose: Real-Time Assisted Writing

Open access
Chen, Mia Xu, Lee, Benjamin N., Bansal, Gagan, Cao, Yuan, Zhang, Shuyuan, Lu, Justin, Tsay, Jackie, Wang, Yinan, Dai, Andrew M., Chen, Zhifeng, Sohn, Timothy, Wu, Yonghui · 2019 · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.

Abstract

In this paper, we present Smart Compose, a novel system for generating interactive, real-time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In the design and deployment of such a large-scale and complicated system, we faced several challenges including model selection, performance evaluation, serving and other practical issues. At the core of Smart Compose is a large-scale neural language model. We leveraged state-of-the-art machine learning techniques for language model training which enabled high-quality suggestion prediction, and constructed novel serving infrastructure for high-throughput and real-time inference. Experimental results show the effectiveness of our proposed system design and deployment approach. This system is currently being served in Gmail.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3292500.3330723

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Figures

Image 1
CC-BY-NC-ND · From the PDF
Figure 2 Smart Compose language generation as language model tasks.
Figure 2 Smart Compose language generation as language model tasks.CC-BY-NC-ND · From the PDF
Figure 3 Smart Compose language generation as a Seq2Seq task.
Figure 3 Smart Compose language generation as a Seq2Seq task.CC-BY-NC-ND · From the PDF
Figure 4 Offline evaluation on personal model with different blending weights.
Figure 4 Offline evaluation on personal model with different blending weights.CC-BY-NC-ND · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

5 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 7

  1. Yoshua Bengio, Réjean Ducharme, Pascal Vincent, , and Christian Jauvin. 2003. A Neural Probabilistic Language Model. Journal of Machine Learning Research (2003).
  2. Nicholas Carlini, Chang Liu, Jernej Kos, Úlfar Erlingsson, and Dawn Song. 2018. The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets. CoRR abs/1802.08232 (2018). arXiv:1802.08232 http://arxiv. org/abs/1802.08232 · arXiv
  3. Google. 2019. Google Cloud TPU. https://cloud.google.com/tpu/. Online; accessed 25 January 2019.
  4. Daniel Jurafsky and James H. Martin. 2000. Speech and Language Processing. Pearson Education.
  5. Mehryar Mohri. [n. d.]. Finite-state Transducers in Language and Speech Pro- cessing. Computational Linguistics 23, 2 ([n. d.]).
  6. S. Radicati. 2018. Email Statistics Report, 2018-2022. https://www.radicati. com/wp/wp-content/uploads/2018/01/Email_Statistics_Report,_2018-2022_ Executive_Summary.pdf. Online; accessed 25 January 2019.
  7. Konrad Zolna, Devansh Arpit, Dendi Suhubdy, and Yoshua Bengio. 2018. Fraternal Dropout. In International Conference on Learning Representations.

Cited by

See all 175

Metadata

Authors
Chen, M. X., Lee, B. N., Bansal, G., Cao, Y., Zhang, S., Lu, J., Tsay, J., Wang, Y., Dai, A. M., Chen, Z., Sohn, T., & Wu, Y.
Affiliations
Google (United States) (US)
Venue
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Publisher
ACM
Published
2019-07-25
Pages
2287-2295
OpenAlex
W2947160092
Cited by
169
References
46
Citations by year
2026: 25 · 2025: 20 · 2024: 24 · 2023: 24 · 2022: 19 · 2021: 34 · 2020: 20 · 2019: 3
FWCI
7.27
Type
conference paper
Language
en
Open access
Locations
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by-nc-nd)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
Keywords
Gmail, email writing, text prediction, neural language models, high-throughput inference, model selection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.