Extracting Information in a Low-resource Setting: Case Study on Bioinformatics Workflows
This addresses the challenge of improving accessibility and reusability of bioinformatics workflows for researchers, though it is incremental as it applies existing methods to a new domain-specific corpus.
The paper tackled the problem of extracting detailed workflow information from bioinformatics articles in a low-resource setting, achieving a 70.4 F-measure using a SciBERT-based NER model on a new annotated corpus of 52 articles.
Bioinformatics workflows are essential for complex biological data analyses and are often described in scientific articles with source code in public repositories. Extracting detailed workflow information from articles can improve accessibility and reusability but is hindered by limited annotated corpora. To address this, we framed the problem as a low-resource extraction task and tested four strategies: 1) creating a tailored annotated corpus, 2) few-shot named-entity recognition (NER) with an autoregressive language model, 3) NER using masked language models with existing and new corpora, and 4) integrating workflow knowledge into NER models. Using BioToFlow, a new corpus of 52 articles annotated with 16 entities, a SciBERT-based NER model achieved a 70.4 F-measure, comparable to inter-annotator agreement. While knowledge integration improved performance for specific entities, it was less effective across the entire information schema. Our results demonstrate that high-performance information extraction for bioinformatics workflows is achievable.