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

The rapid growth of scientific publications, particularly during the COVID-19pandemic, emphasizes the need for tools to help researchers efficientlycomprehend the latest advancements. One essential part of understandingscientific literature is research aspect classification, which categorizessentences in abstracts to Background, Purpose, Method, and Finding. In thisstudy, we investigate the impact of different datasets on model performance forthe crowd-annotated CODA-19 research aspect classification task. Specifically,we explore the potential benefits of using the large, automatically curatedPubMed 200K RCT dataset and evaluate the effectiveness of large language models(LLMs), such as LLaMA, GPT-3, ChatGPT, and GPT-4. Our results indicate thatusing the PubMed 200K RCT dataset does not improve performance for the CODA-19task. We also observe that while GPT-4 performs well, it does not outperformthe SciBERT model fine-tuned on the CODA-19 dataset, emphasizing the importanceof a dedicated and task-aligned datasets dataset for the target task. Our codeis available at https://github.com/Crowd-AI-Lab/CODA-19-exp.

Good Data, Large Data, or No Data? Comparing Three Approaches in Developing Research Aspect Classifiers for Biomedical Papers