# Efficient Natural Language Response Suggestion for Smart Reply

arXiv: https://arxiv.org/abs/1705.00652 · HTML: https://mlsanity.com/paper/1705.00652/

## Key facts

- Cited by 229 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2017.

## Built on by (most cited first, 30 of 229)

- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning](https://mlsanity.com/paper/2104.06979/) (2021)
- [CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP](https://mlsanity.com/paper/2110.11316/) (2021)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval](https://mlsanity.com/paper/2108.06027/) (2021)
- [LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval](https://mlsanity.com/paper/2103.08784/) (2021)
- [A Statutory Article Retrieval Dataset in French](https://mlsanity.com/paper/2108.11792/) (2021)
- [GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning](https://mlsanity.com/paper/2402.16829/) (2024)
- [TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems](https://mlsanity.com/paper/2311.11315/) (2023)
- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding](https://mlsanity.com/paper/2204.10050/) (2022)
- [Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2309.17050/) (2023)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)
- [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://mlsanity.com/paper/2401.07883/) (2024)
- [UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining](https://mlsanity.com/paper/2202.13469/) (2022)
- [QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations](https://mlsanity.com/paper/2305.11694/) (2023)
- [Non-Contrastive Learning Meets Language-Image Pre-Training](https://mlsanity.com/paper/2210.09304/) (2022)
- [A Proposed Conceptual Framework for a Representational Approach to Information Retrieval](https://mlsanity.com/paper/2110.01529/) (2021)
- [LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval](https://mlsanity.com/paper/2203.06169/) (2022)
- [Decoupled Context Processing for Context Augmented Language Modeling](https://mlsanity.com/paper/2210.05758/) (2022)
- [Artificial intelligence in communication impacts language and social relationships](https://mlsanity.com/paper/2102.05756/) (2021)
- [Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning](https://mlsanity.com/paper/2311.08110/) (2023)
- [Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT](https://mlsanity.com/paper/2402.07440/) (2024)
- [DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2109.12599/) (2021)

## Abstract (arXiv)

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.