Back to Search Start Over

Towards Content Transfer through Grounded Text Generation

Authors :
Prabhumoye, Shrimai
Quirk, Chris
Galley, Michel
Source :
Proc. NAACL 2019
Publication Year :
2019

Abstract

Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper introduces the notion of Content Transfer for long-form text generation, where the task is to generate a next sentence in a document that both fits its context and is grounded in a content-rich external textual source such as a news story. Our experiments on Wikipedia data show significant improvements against competitive baselines. As another contribution of this paper, we release a benchmark dataset of 640k Wikipedia referenced sentences paired with the source articles to encourage exploration of this new task.

Details

Database :
arXiv
Journal :
Proc. NAACL 2019
Publication Type :
Report
Accession number :
edsarx.1905.05293
Document Type :
Working Paper