2019
NIPS
NeurIPS 2019
Sequence Modeling with Unconstrained Generation Order
Abstract
The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary order. Our model learns decoding order as a result of its training procedure. Our experiments show that this model is superior to fixed order models on a number of sequence generation tasks, such as Machine Translation, Image-to-LaTeX and Image Captioning.
🌉
Interdisciplinary Bridge
— Deep Learning and Natural Language Processing
📈
Trend Setter
— Image Captioning
🧭
Keyword Pioneer
— unconstrained generation
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Natural Language Processing > Generation > Text Generation
Natural Language Processing > Applications > Machine Translation
Natural Language Processing > Generation > Machine Translation
Deep Learning > Learning Types > Generative Models
Natural Language Processing > Applications > Image Captioning
Deep Learning > Learning Types > Sequence Modeling