Surfer100: Generating Surveys From Web Resources, Wikipedia-style
Abstract
Fast-developing fields such as Artificial Intelligence (AI) often outpace the efforts of encyclopedic sources such as Wikipedia, which either do not completely cover recently-introduced topics or lack such content entirely. As a result, methods for automatically producing content are valuable tools to address this information overload. We show that recent advances in pretrained language modeling can be combined for a two-stage extractive and abstractive approach for Wikipedia lead paragraph generation. We extend this approach to generate longer Wikipedia-style summaries with sections and examine how such methods struggle in this application through detailed studies with 100 reference human-collected surveys. This is the first study on utilizing web resources for long Wikipedia-style summaries to the best of our knowledge.
Cite
@article{arxiv.2112.06377,
title = {Surfer100: Generating Surveys From Web Resources, Wikipedia-style},
author = {Irene Li and Alexander Fabbri and Rina Kawamura and Yixin Liu and Xiangru Tang and Jaesung Tae and Chang Shen and Sally Ma and Tomoe Mizutani and Dragomir Radev},
journal= {arXiv preprint arXiv:2112.06377},
year = {2022}
}
Comments
LREC 2022, main conference