Convolutional Sequence to Sequence Learning
Explore this paper's citation graph
Summary
This work introduces an architecture based entirely on convolutional neural networks, which outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT-French translation at an order of magnitude faster speed, both on GPU and CPU.
- Type
- preprint
- Published
- 2017-05-08
- Cited by
- 3,552
- References
- 51
- Access
- Open access
- OpenAlex
- https://openalex.org/W2613904329
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3648736
Keywords
Sequence (biology), Computer science, Sequence learning, Artificial intelligence, Biology
References
- On the importance of initialization and momentum in deep learning
- Torch7: A Matlab-like Environment for Machine Learning
- Attention-Based Models for Speech Recognition
- Understanding the difficulty of training deep feedforward neural networks
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- End-To-End Memory Networks
- On the difficulty of training recurrent neural networks
- Neural Machine Translation of Rare Words with Subword Units
- A Neural Attention Model for Abstractive Sentence Summarization
- Effective Approaches to Attention-based Neural Machine Translation
- DUC in context
- Long Short-Term Memory
- Dropout: a simple way to prevent neural networks from overfitting
- Finding Structure in Time
- Phoneme recognition using time-delay neural networks
- Japanese and Korean voice search
- Encoding Source Language with Convolutional Neural Network for Machine Translation
- A Simple, Fast, and Effective Reparameterization of IBM Model 2
- ROUGE: A Package for Automatic Evaluation of Summaries
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cited by
- Deep Reinforcement Learning: An Overview
- Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
- Deep Extreme Multi-label Learning
- Dependency Parsing with Dilated Iterated Graph CNNs
- Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU
- A General-Purpose Tagger with Convolutional Neural Networks
- A Fully Trainable Network with RNN-based Pooling
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Single-Queue Decoding for Neural Machine Translation
- Unified detection system for automatic, real-time, accurate animal detection in camera trap images from the arctic tundra
- Deep architectures for Neural Machine Translation
- Learning to Align the Source Code to the Compiled Object Code
- MusiteDeep: a deep‐learning framework for general and kinase‐specific phosphorylation site prediction
- Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
- Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks
- Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification
- Author Profiling with Bidirectional RNNs using Attention with GRUs
- Deliberation Networks: Sequence Generation Beyond One-Pass Decoding
- MuseGAN: Symbolic-domain Music Generation and Accompaniment with Multi-track Sequential Generative Adversarial Networks
- Parallelizing Linear Recurrent Neural Nets Over Sequence Length
Related papers
- ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ
- Using DataGrid Control to Realize DataBase of Querying in VB6.0
- Study and Two Types of Typical Usage of DataGrid Web Server Control
- PACWON: A parallelizing compiler for workstations on a network
- Data-driven sequence learning or search: What are the prerequisites for the generation of explicit sequence knowledge?
- Disentangled Self-Supervision in Sequential Recommenders
- Toward Understanding Catastrophic Forgetting in Continual Learning