On-The-Fly Information Retrieval Augmentation for Language Models

NARRATIVE UNDERSTANDING, STORYLINES, AND EVENTS(2020)

Cited 6|Views89
No score
Abstract
Here 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.
More
Translated text
Key words
information retrieval,models,language,on-the-fly
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined