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

Biomedical summarization requires large datasets to train for textgeneration. We show that while transfer learning offers a viable option foraddressing this challenge, an in-domain pre-training does not always offeradvantages in a BioASQ summarization task. We identify a suitable modelarchitecture and use it to show a benefit of a general-domain pre-trainingfollowed by a task-specific fine-tuning in the context of a BioASQsummarization task, leading to a novel three-step fine-tuning approach thatworks with only a thousand in-domain examples. Our results indicate that aLarge Language Model without domain-specific pre-training can have asignificant edge in some domain-specific biomedical text generation tasks.

Enhancing Biomedical Text Summarization and Question-Answering: On the Utility of Domain-Specific Pre-Training