Open AccessPosted Content
Efficient Natural Language Response Suggestion for Smart Reply
Matthew L. Henderson,Rami Al-Rfou,Brian Strope,Yun-Hsuan Sung,László Lukács,Ruiqi Guo,Sanjiv Kumar,Balint Miklos,Ray Kurzweil +8 more
Reads0
Chats0
TLDR
A computationally efficient machine-learned method for natural language response suggestion using feed-forward neural networks using n-gram embedding features that achieves the same quality at a small fraction of the computational requirements and latency.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.read more
Citations
More filters
Journal ArticleDOI
Adapting Sentence Transformers for the Aviation Domain
TL;DR: In this article , a two-stage process consisting of pre-training followed by fine-tuning is proposed for adapting sentence transformers for the aviation domain, which has unique characteristics such as technical jargon, abbreviations, and unconventional grammar.
Proceedings ArticleDOI
Augmenting Poetry Composition with Verse by Verse
TL;DR: Uthus et al. as discussed by the authors presented a paper on the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track.
Posted Content
Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions.
TL;DR: The authors explored low-cost model compression techniques like Layer Dropping and Layer Freezing to improve the quality of reply suggestion systems, but at the cost of unsustainable training times, and demonstrated the efficacy of these techniques in large-data scenarios, enabling the training time reduction for a commercial email reply suggestion system.
Journal ArticleDOI
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning
TL;DR: In this article , a relevance model via contrastive learning from a pre-trained language model was trained to perceive the contextual relevance between a query embedding and indexed mobile features. And to make it efficiently run on-device using minimal resources, applied knowledge distillation to compress the model without degrading much performance.
Posted Content
A Dataset and Baselines for Multilingual Reply Suggestion
TL;DR: This article presented MRS, a multilingual reply suggestion dataset with ten languages, which can be used to compare two families of models: 1) retrieval models that select the reply from a fixed set and 2) generation models that produce the reply directly from scratch.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Posted Content
Efficient Estimation of Word Representations in Vector Space
TL;DR: This paper proposed two novel model architectures for computing continuous vector representations of words from very large data sets, and the quality of these representations is measured in a word similarity task and the results are compared to the previously best performing techniques based on different types of neural networks.
Posted Content
Sequence to Sequence Learning with Neural Networks
TL;DR: This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
Proceedings ArticleDOI
TensorFlow: a system for large-scale machine learning
Martín Abadi,Paul Barham,Jianmin Chen,Zhifeng Chen,Andy Davis,Jeffrey Dean,Matthieu Devin,Sanjay Ghemawat,Geoffrey Irving,Michael Isard,Manjunath Kudlur,Josh Levenberg,Rajat Monga,Sherry Moore,Derek G. Murray,Benoit Steiner,Paul A. Tucker,Vijay K. Vasudevan,Pete Warden,Martin Wicke,Yuan Yu,Xiaoqiang Zheng +21 more
TL;DR: TensorFlow as mentioned in this paper is a machine learning system that operates at large scale and in heterogeneous environments, using dataflow graphs to represent computation, shared state, and the operations that mutate that state.