A Search Engine for Discovery of Scientific Challenges and Directions

TL;DR

This paper introduces a novel search engine for scientific challenges and directions, using an expert-annotated corpus and models trained to facilitate rapid knowledge discovery across disciplines, especially in biomedicine and AI.

Contribution

It presents a new task, annotated dataset, and search engine for extracting and searching scientific challenges and directions, improving discovery over existing tools.

Findings

Outperforms popular scientific search engines in aiding knowledge discovery.

Models trained on the dataset generalize across biomedical and AI domains.

The resource is publicly available for broader research use.

Abstract

Keeping track of scientific challenges, advances and emerging directions is a fundamental part of research. However, researchers face a flood of papers that hinders discovery of important knowledge. In biomedicine, this directly impacts human lives. To address this problem, we present a novel task of extraction and search of scientific challenges and directions, to facilitate rapid knowledge discovery. We construct and release an expert-annotated corpus of texts sampled from full-length papers, labeled with novel semantic categories that generalize across many types of challenges and directions. We focus on a large corpus of interdisciplinary work relating to the COVID-19 pandemic, ranging from biomedicine to areas such as AI and economics. We apply a model trained on our data to identify challenges and directions across the corpus and build a dedicated search engine. In experiments with 19 researchers and clinicians using our system, we outperform a popular scientific search engine in assisting knowledge discovery. Finally, we show that models trained on our resource generalize to the wider biomedical domain and to AI papers, highlighting its broad utility. We make our data, model and search engine publicly available. https://challenges.apps.allenai.org/