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

Automated knowledge curation for biomedical ontologies is key to ensure thatthey remain comprehensive, high-quality and up-to-date. In the era offoundational language models, this study compares and analyzes three NLPparadigms for curation tasks: in-context learning (ICL), fine-tuning (FT), andsupervised learning (ML). Using the Chemical Entities of Biological Interest(ChEBI) database as a model ontology, three curation tasks were devised. ForICL, three prompting strategies were employed with GPT-4, GPT-3.5, BioGPT.PubmedBERT was chosen for the FT paradigm. For ML, six embedding models wereutilized for training Random Forest and Long-Short Term Memory models. Fivesetups were designed to assess ML and FT model performance across differentdata availability scenarios.Datasets for curation tasks included: task 1(620,386), task 2 (611,430), and task 3 (617,381), maintaining a 50:50 positiveversus negative ratio. For ICL models, GPT-4 achieved best accuracy scores of0.916, 0.766 and 0.874 for tasks 1-3 respectively. In a direct comparison, ML(trained on ~260,000 triples) outperformed ICL in accuracy across all tasks.(accuracy differences: +.11, +.22 and +.17). Fine-tuned PubmedBERT performedsimilarly to leading ML models in tasks 1 & 2 (F1 differences: -.014 and+.002), but worse in task 3 (-.048). Simulations revealed performance declinesin both ML and FT models with smaller and higher imbalanced training data.where ICL (particularly GPT-4) excelled in tasks 1 & 3. GPT-4 excelled in tasks1 and 3 with less than 6,000 triples, surpassing ML/FT. ICL underperformedML/FT in task 2.ICL-augmented foundation models can be good assistants forknowledge curation with correct prompting, however, not making ML and FTparadigms obsolete. The latter two require task-specific data to beat ICL. Insuch cases, ML relies on small pretrained embeddings, minimizing computationaldemands.

Benchmarking and Analyzing In-context Learning, Fine-tuning and  Supervised Learning for Biomedical Knowledge Curation: a focused study on  chemical entities of biological interest