TOPICAL: TOPIC Pages AutomagicaLly

TL;DR

This paper presents TOPICAL, an automated system for generating high-quality biomedical topic pages by combining retrieval, clustering, and prompting, enabling rapid curation of scientific information with high relevance and accuracy.

Contribution

The paper introduces TOPICAL, a novel automated pipeline for creating biomedical topic pages, including a web app and open-source code, focusing on scientific entities.

Findings

Most generated pages were relevant and accurate.

Supporting citations were correctly included.

The system enables on-demand creation of biomedical topic pages.

Abstract

Topic pages aggregate useful information about an entity or concept into a single succinct and accessible article. Automated creation of topic pages would enable their rapid curation as information resources, providing an alternative to traditional web search. While most prior work has focused on generating topic pages about biographical entities, in this work, we develop a completely automated process to generate high-quality topic pages for scientific entities, with a focus on biomedical concepts. We release TOPICAL, a web app and associated open-source code, comprising a model pipeline combining retrieval, clustering, and prompting, that makes it easy for anyone to generate topic pages for a wide variety of biomedical entities on demand. In a human evaluation of 150 diverse topic pages generated using TOPICAL, we find that the vast majority were considered relevant, accurate, and coherent, with correct supporting citations. We make all code publicly available and host a free-to-use web app at: https://s2-topical.apps.allenai.org