Training and testing data are now available for the 2024 Plain Language Adaptation of Biomedical Abstractshttps://bionlp.nlm.nih.gov/plaba2024/ track at TREChttps://trec.nist.gov.
The PLABA task is to rewrite biomedical abstracts, line by line, in plain language for the general public. This includes:
- Simplifying and splitting sentences
- Replacing or omitting jargon
- Providing further background where appropriate
This year, PLABA also has new subtask—expert term replacement. This includes:
- Identifying expert terms
- Classifying how they should be replaced (explained, substituted, generalized, exemplified, or omitted)
- Generating replacement text for the terms
As this subtask does not require generation of complete documents, we hope it will allow for participation with fewer compute resources.
By participating in PLABA, you will get:
- Access to a unique, manually annotated expert term replacement dataset
- Manual evaluations of system outputs by science communication experts
Further information
Task descriptions: https://bionlp.nlm.nih.gov/plaba2024/
Registration: https://ir.nist.gov/evalbase/
Mailing list: https://groups.google.com/g/plaba2024
Due dates
Aug 30 - Task 2 (abstract rewriting) submissions due
Sep 15 - Task 1 (term replacement) submissions due
We look forward to your submissions!