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.
| Original language | English (US) |
|---|---|
| Pages | 1-11 |
| Number of pages | 11 |
| State | Published - 2024 |
| Event | 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024 - Hybrid, Mexico City, Mexico Duration: Jun 16 2024 → Jun 21 2024 |
Conference
| Conference | 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024 |
|---|---|
| Country/Territory | Mexico |
| City | Hybrid, Mexico City |
| Period | 6/16/24 → 6/21/24 |
Funding
This research was enabled in part by support provided by the Digital Research Alliance of Canada (alliancecan.ca) and Compute Ontario (www.computeontario.ca). We thank Jenna Sparks, Erin Bransom, and Bailey Kuehl for helping to conduct human evaluations. We thank the AI2 Reviz team for assistance with hosting the web application. We thank all internal and external reviewers for their thoughtful feedback, which improved earlier drafts of this manuscript.
ASJC Scopus subject areas
- Computer Networks and Communications
- Hardware and Architecture
- Information Systems
- Software