2020
ACL
ACL 2020
On-The-Fly Information Retrieval Augmentation for Language Models
Abstract
AbstractHere we experiment with the use of information retrieval as an augmentation for pre-trained language models. The text corpus used in information retrieval can be viewed as form of episodic memory which grows over time. By augmenting GPT 2.0 with information retrieval we achieve a zero shot 15% relative reduction in perplexity on Gigaword corpus without any re-training. We also validate our IR augmentation on an event co-reference task.
🌉
Interdisciplinary Bridge
— Deep Learning and Machine Learning and Natural Language Processing
📈
Trend Setter
— Retrieval-Augmented Generation
🧭
Keyword Pioneer
— language model augmentation
🐣
Hot Topic Early Bird
— retrieval-augmented 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
Machine Learning > Learning Types > Zero-Shot Learning
Natural Language Processing > Generation > Language Modeling
Natural Language Processing > Applications > Information Retrieval
Natural Language Processing > Resources & Methods > Large Language Models
Natural Language Processing > Resources & Methods > Retrieval-Augmented Generation
Deep Learning > Learning Types > Retrieval-Augmented Generation