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
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
Posted Content
Augmenting Poetry Composition with Verse by Verse.
TL;DR: In this paper, a group of AI poets, styled after various American classic poets, are able to offer as suggestions generated lines of verse while a user is composing a poem, and a dual-encoder model is tasked with recommending the next possible set of verses from our index given the previous line of verse.
Proceedings ArticleDOI
SPBERTQA: A Two-Stage Question Answering System Based on Sentence Transformers for Medical Texts
Nhung T. M. Nguyen,Phuong Phan-Dieu Ha,Luan Thanh Nguyen,Kiet Van Nguyen,Ngan Luu-Thuy Nguyen +4 more
TL;DR: This paper proposes a two-stage QA system based on Sentence-BERT (SBERT) using multiple negatives ranking (MNR) loss combined with BM25, and achieves better performance than traditional methods.
Journal ArticleDOI
SupMPN: Supervised Multiple Positives and Negatives Contrastive Learning Model for Semantic Textual Similarity
TL;DR: The proposed SupMPN is a Supervised Multiple Positives and Negatives Contrastive Learning Model, which accepts multiple hard-positive sentences and multiplehard-negative sentences simultaneously and then tries to bring similar sentences closer together in the representation space by discrimination among multiple similar and dissimilar sentences.
Journal ArticleDOI
Who Wrote this? How Smart Replies Impact Language and Agency in the Workplace
TL;DR: In this paper , the authors propose a loss of agency theory to study the impact of AI on human agency, focusing on the transfer of agency that is forced by circumstances such as time pressure, human weaknesses (such as complacency), and conceptual priming.
Patent
Multi-scale model for semantic matching
TL;DR: This article proposed a method for estimating a quality of semantic match of a first sentence to a second sentence by outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, and then comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy.
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.