Surfer100: Generating Surveys From Web Resources, Wikipedia-style

TL;DR

This paper presents Surfer100, a method that combines extractive and abstractive techniques using pretrained language models to generate comprehensive Wikipedia-style surveys from web resources, addressing the challenge of rapidly evolving fields.

Contribution

It introduces a novel two-stage approach for generating long, structured summaries from web data, extending existing methods to produce detailed Wikipedia-like surveys.

Findings

Effective in generating structured summaries with sections

Struggles identified in maintaining factual accuracy and coherence

First study to utilize web resources for long Wikipedia-style summaries

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.