• Home
  • Search
  • An open-set semi-supervised multi-task learning framework for context classification in biomedical texts.
  • https://doi.org/10.1016/j.jbi.2025.104886Copy DOI Icon

An open-set semi-supervised multi-task learning framework for context classification in biomedical texts.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

In biomedical research, knowledge about the relationships between entities, including genes, proteins, and drugs, is vital for elucidating complex biological processes and intracellular pathway mechanisms. While natural language processing (NLP) methods have shown great success in biomedical relation extraction (RE), extracted relations often lack contextual information such as cell type, cell line, and intracellular location. Previous studies treated this problem as a post hoc context-relation association task, limited by the absence of a golden standard corpus and prone to error propagation. To address these challenges, we propose CELESTA (Context Extraction through LEarning with Semi-supervised multi-Task Architecture), an open-set semi-supervised multi-task learning (OSSL-MTL) framework for biomedical context classification. We designed a multi-task learning (MTL) architecture that integrates with the semi-supervised learning (SSL) strategies to leverage unlabeled data containing both in-distribution (ID) and out-of-distribution (OOD) examples. We created a large-scale dataset consisting of five context classification tasks by curating two large Biological Expression Language (BEL) corpora and annotating them with our new entity span annotation method. Additionally, we developed an OOD detector to distinguish between ID and OOD instances within the unlabeled data and applied data augmentation with an external database to enrich our dataset. Extensive experiments show that our framework significantly improves context classification performance. Our best OSSL-MTL models achieve F1 scores of 77.75% and 82.87% on location and disease classification tasks, and the SSL-MTL models without OOD detection perform best for cell line and cell type classification. The OOD detection experiment confirms that the OOD detector effectively identifies unknown categories while maintaining ID accuracy. Qualitative analysis shows improved extraction of implicit contexts compared to baseline models. Our analysis demonstrates the effectiveness of the framework CELESTA in improving context classification and extracting contextual information with high accuracy. The newly created dataset and code are publicly available on GitHub (https://github.com/pitt-miskov-zivanov-lab/CELESTA).

Similar Papers
  • Research Article
  • Citations69

A semi-supervised multi-task learning framework for cancer classification with weak annotation in whole-slide images.

  • Jan 01, 2023
  • Medical Image Analysis
  • Zeyu Gao +10
  • Research Article
  • Citations1

Semi-supervised deep learning for uterus and bladder segmentation on female pelvic floor magnetic resonance imaging with limited labeled data.

  • Oct 01, 2025
  • American journal of obstetrics and gynecology
  • Jianwei Zuo +5
  • Research Article
  • Citations188

A Fully Automated Multimodal MRI-Based Multi-Task Learning for Glioma Segmentation and IDH Genotyping.

  • Jun 01, 2022
  • IEEE Transactions on Medical Imaging
  • Jianhong Cheng +3
  • Conference Article
  • Citations7

Semi-Supervised Life-Long Learning with Application to Sensing

  • Dec 01, 2007
  • Qiuhua Liu +2
  • Research Article
  • Citations65

Semi-Supervised Concept Learning by Concept-Cognitive Learning and Concept Space

  • Jul 21, 2020
  • IEEE Transactions on Knowledge and Data Engineering
  • Yunlong Mi +3
  • Research Article
  • Citations70

Exploring semi-supervised variational autoencoders for biomedical relation extraction.

  • Feb 27, 2019
  • Methods (San Diego, Calif.)
  • Yijia Zhang +1
  • Research Article
  • Citations33

FSELM: fusion semi-supervised extreme learning machine for indoor localization with Wi-Fi and Bluetooth fingerprints

  • Apr 06, 2018
  • Soft Computing
  • Xinlong Jiang +4
  • Research Article

A novel adaptive safe semi-supervised learning framework for pattern extraction and classification

  • Jan 01, 2024
  • AIMS Mathematics
  • Jun Ma +2
  • Conference Article
  • Citations5

ActiveMatch: End-To-End Semi-Supervised Active Representation Learning

  • Oct 16, 2022
  • Xinkai Yuan +2
  • Research Article
  • Citations28

Semi-supervised extreme learning machine with manifold and pairwise constraints regularization

  • Oct 07, 2014
  • Neurocomputing
  • Yong Zhou +3
  • Conference Article
  • Citations13

A multi-task learning based approach to biomedical entity relation extraction

  • Dec 01, 2018
  • Qingqing Li +9
  • Research Article

Edge-Optimized Semi-Supervised Deep Learning for Power Line Component Inspection.

  • Jun 23, 2026
  • Sensors (Basel, Switzerland)
  • Nico Surantha +2
  • Conference Article
  • Citations8

Online Semi-Supervised Multi-task Distance Metric Learning

  • Dec 01, 2016
  • Ya Li +1
  • Book Chapter
  • Citations145

Semi-supervised Deep Learning for Fully Convolutional Networks

  • Jan 01, 2017
  • Christoph Baur +2
  • Conference Article
  • Citations2

Learning from Web Data: Improving Crowd Counting via Semi-Supervised Learning

  • Jan 10, 2021
  • Tao Peng +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.