English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Keeping track of scientific challenges, advances and emerging directions is afundamental part of research. However, researchers face a flood of papers thathinders discovery of important knowledge. In biomedicine, this directly impactshuman lives. To address this problem, we present a novel task of extraction andsearch of scientific challenges and directions, to facilitate rapid knowledgediscovery. We construct and release an expert-annotated corpus of texts sampledfrom full-length papers, labeled with novel semantic categories that generalizeacross many types of challenges and directions. We focus on a large corpus ofinterdisciplinary work relating to the COVID-19 pandemic, ranging frombiomedicine to areas such as AI and economics. We apply a model trained on ourdata to identify challenges and directions across the corpus and build adedicated search engine. In experiments with 19 researchers and cliniciansusing our system, we outperform a popular scientific search engine in assistingknowledge discovery. Finally, we show that models trained on our resourcegeneralize to the wider biomedical domain and to AI papers, highlighting itsbroad utility. We make our data, model and search engine publicly available.https://challenges.apps.allenai.org/

A Search Engine for Discovery of Scientific Challenges and Directions