2017
IJCNLP
IJCNLP 2017
Distributional Modeling on a Diet: One-shot Word Learning from Text Only
Abstract
AbstractWe test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative.
🧭
Keyword Pioneer
— text only
🐣
Hot Topic Early Bird
— one-shot learning
🐝
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