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
Proceedings ArticleDOI
Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
TL;DR: Experimental results show that retrofitting multilingual sentence embeddings with AMR leads to better state-of-the-art performance on both semantic textual similarity and transfer tasks.
Proceedings ArticleDOI
Unsupervised Co-Segmentation for Athlete Movements and Live Commentaries Using Crossmodal Temporal Proximity
TL;DR: In this paper, a guided attention scheme was employed to detect and utilize temporal co-occurrences of audio and video information to perform unsupervised audio-visual co-segmentation.
Back to the Roots: Predicting the Source Domain of Metaphors using Contrastive Learning
TL;DR: This paper propose a contrastive learning approach that ranks source domains by their likelihood of being referred to in a metaphorical text, which achieves reasonable performance even for rare source domains. But it requires a large set of source domains to be considered.
Proceedings ArticleDOI
MacNabbs: Knowledge Extraction from Unstructured Data using Semantic Analysis and User Activity Logging
TL;DR: An approach which uses topic modeling and anomaly detection to point out the information that may be of particular interest to a domain expert to suggest decision options based on the analyzed data and user's activity is presented.
Journal Article
BERTicsson: A Recommender System For Troubleshooting
TL;DR: BERTicsson is presented, a BERT-based model that uses two main stages for retrieving a shortlist of candidate answers for new problems and raking them accordingly, and significantly improves the accuracy of the recommended answers compared to non-BERT models, such as BM25.
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.