The reviewed record of science sign in
Pith

arxiv: 1705.00652 · v1 · pith:QT26B7RW · submitted 2017-05-01 · cs.CL

Efficient Natural Language Response Suggestion for Smart Reply

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:QT26B7RWrecord.jsonopen to challenge →

classification cs.CL
keywords responseefficientlanguagemethodnaturaloptimizedsuggestionachieves
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

    cs.CL 2026-06 unverdicted novelty 8.0

    SkMTEB is the first comprehensive text embedding benchmark for Slovak, and vocabulary-trimmed E5 adaptations achieve competitive performance with much smaller models.

  2. SimCSE: Simple Contrastive Learning of Sentence Embeddings

    cs.CL 2021-04 conditional novelty 8.0

    SimCSE achieves 76.3% unsupervised and 81.6% supervised Spearman's correlation on STS tasks with BERT-base, improving prior best results by 4.2% and 2.2% via simple contrastive learning.

  3. Dense Passage Retrieval for Open-Domain Question Answering

    cs.CL 2020-04 accept novelty 8.0

    Dense dual-encoder retrievers outperform BM25 by 9-19% absolute in top-20 passage retrieval accuracy across open-domain QA datasets and enable new state-of-the-art end-to-end QA results.

  4. ProtSent: Protein Sentence Transformers

    cs.LG 2026-05 unverdicted novelty 7.0

    Contrastive fine-tuning of protein language models on Pfam, structural, interaction, and mutational datasets produces embeddings that improve kNN performance on 15-16 of 23 downstream tasks including remote homology d...

  5. Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

    cs.CL 2026-06 unverdicted novelty 6.0

    Permutation-invariant fine-tuning (PI-FT) randomizes field order and applies dropout during embedding model training to eliminate sensitivity to serialization order, reducing order-change penalty from 7.4 to 0.2 nDCG@...

  6. LCSHBench: A Multilingual, Consensus-Grounded Benchmark for Library of Congress Subject Heading Assignment

    cs.DL 2026-06 unverdicted novelty 6.0

    LCSHBench supplies a consensus-filtered multilingual dataset for LCSH assignment evaluation together with exact and concept-level metrics, and reports that fine-tuning a 300M embedder yields higher exact recall@200 th...

  7. To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios

    cs.LG 2026-05 conditional novelty 6.0

    Text embeddings are robust to truncation without MRL except when reducing size by at least 80%.

  8. ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation

    cs.CL 2026-04 unverdicted novelty 6.0

    ORPHEAS, a Greek-English embedding model created with knowledge graph fine-tuning, outperforms state-of-the-art multilingual models on monolingual and cross-lingual retrieval benchmarks.

  9. REPLUG: Retrieval-Augmented Black-Box Language Models

    cs.CL 2023-01 conditional novelty 6.0

    REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.

  10. To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios

    cs.LG 2026-05 unverdicted novelty 5.0

    Truncated embeddings from non-MRL models perform comparably to or better than MRL-trained models for most truncation levels, except heavy truncation of 80% or more.

  11. Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts

    cs.CL 2026-04 unverdicted novelty 5.0

    Domain-adapted utterance-level retrieval raises Cohen's kappa for tutoring dialogue act annotation to 0.526-0.580 on TalkMoves and 0.659-0.743 on Eedi, beating no-retrieval baselines by large margins across three LLMs.

  12. Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval

    cs.IR 2025-04 unverdicted novelty 5.0

    LLM-generated synthetic hard negatives for training dense retrievers consistently underperform corpus-mined negatives from BM25 and cross-encoders across 10 BEIR datasets, with non-monotonic gains from scaling the gen...

  13. Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability

    cs.IR 2026-05 unverdicted novelty 4.0

    CoveR improves nugget coverage by 10% over dense baselines in long-form RAG via coverage-aware contrastive training on LLM-generated sub-question signals without losing relevance performance.

  14. The Multilingual Curse at the Retrieval Layer: Evidence from Amharic

    cs.IR 2026-05 unverdicted novelty 4.0

    Zero-shot multilingual retrievers underperform monolingual Amharic models by 23% relative MRR@10; fine-tuned multilingual models still trail the best monolingual baseline.

  15. Reinforced Preference Optimization for Reasoning-Augmented Recommendations

    cs.IR 2026-05 unverdicted novelty 4.0

    RPORec unifies LLM reasoning with a recommendation head through reasoning-augmented modeling and reinforced preference optimization to improve recommendation accuracy and interpretability.

  16. Unified Supervision for Walmart's Sponsored Search Retrieval via Joint Semantic Relevance and Behavioral Engagement Modeling

    cs.IR 2026-04 unverdicted novelty 4.0

    A hybrid supervision method for bi-encoder retrievers combines graded relevance from teacher models, production retrieval priors, and selective engagement to improve relevance and NDCG over Walmart's current sponsored...

  17. OCC: A Smart Reply System for Efficient In-App Communications

    cs.CL 2019-07 unverdicted novelty 3.0

    Uber's OCC system uses unsupervised embeddings plus nearest-neighbor intent detection followed by historical reply retrieval, reporting 76% intent accuracy and 71% production usage in English-speaking countries.