# Extracting Information in a Low-resource Setting: Case Study on Bioinformatics Workflows

arXiv: https://arxiv.org/abs/2411.19295 · HTML: https://mlsanity.com/paper/2411.19295/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Builds on (most cited first, 8 of 8)

- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer](https://mlsanity.com/paper/2311.08526/) (2023)
- [Fast Vocabulary Transfer for Language Model Compression](https://mlsanity.com/paper/2402.09977/) (2024)
- [NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging](https://mlsanity.com/paper/2112.00405/) (2021)
- [AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain](https://mlsanity.com/paper/2110.13434/) (2021)
- [Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting](https://mlsanity.com/paper/2402.12801/) (2024)
- [DMDD: A Large-Scale Dataset for Dataset Mentions Detection](https://mlsanity.com/paper/2305.11779/) (2023)
- [A large dataset of software mentions in the biomedical literature](https://mlsanity.com/paper/2209.00693/) (2022)

## Built on by (most cited first, 1 of 1)

- [Supporting Workflow Reproducibility by Linking Bioinformatics Tools across Papers and Executable Code](https://mlsanity.com/paper/2603.08195/) (2026)

## Abstract (arXiv)

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.