A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes

Published in

International Conference on Language Resources ...(2022)

External Links:

Generate Graph

TL;DR

ChemDisGene, a new dataset for training and evaluating multi-class multi-label biomedical relation extraction models, is introduced, which is both substantially larger and cleaner; it also includes annotations linking mentions to their entities.

Abstract

We introduce ChemDisGene, a new dataset for training and evaluating multi-class multi-label biomedical relation extraction models. Our dataset contains 80k biomedical research abstracts labeled with mentions of chemicals, diseases, and genes, portions of which human experts labeled with 18 types of biomedical relationships between these entities (intended for evaluation), and the remainder of which (intended for training) has been distantly labeled via the CTD database with approximately 78% accuracy. In comparison to similar preexisting datasets, ours is both substantially larger and cleaner; it also includes annotations linking mentions to their entities. We also provide three baseline deep neural network relation extraction models trained and evaluated on our new dataset.

Authors

A. McCallum

17 papers

Sunil Mohan

2 papers

M. Torkar

2 papers

References41 items

DrugProt corpus: Biocreative VII Track 1 - Text mining drug and chemical-protein interactions

Re-TACRED: Addressing Shortcomings of the TACRED Dataset

Knowledge Network Embedding of Transcriptomic Data from Spaceflown Mice Uncovers Signs and Symptoms Associated with Terrestrial Diseases

Comparative Toxicogenomics Database (CTD): update 2021

Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing

A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes

Published in

International Conference on Language Resources ...(2022)

External Links:

Generate Graph

TL;DR

Abstract

Authors

A. McCallum

17 papers

Sunil Mohan

2 papers

M. Torkar

2 papers

References41 items

DrugProt corpus: Biocreative VII Track 1 - Text mining drug and chemical-protein interactions

Re-TACRED: Addressing Shortcomings of the TACRED Dataset

Knowledge Network Embedding of Transcriptomic Data from Spaceflown Mice Uncovers Signs and Symptoms Associated with Terrestrial Diseases

Comparative Toxicogenomics Database (CTD): update 2021

Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing

Dongxu Zhang

1 papers

Neural networks for open and closed Literature-based Discovery

Network medicine framework for identifying drug-repurposing opportunities for COVID-19

TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task

Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network

Matching the Blanks: Distributional Similarity for Relation Learning

PubTator central: automated concept annotation for biomedical full text articles

RENET: A Deep Learning Approach for Extracting Gene-Disease Associations from Literature

A Computational Framework for Genome-wide Characterization of the Human Disease Landscape.

Overview of the BioCreative VI Precision Medicine Track: mining protein interactions and mutations for precision medicine

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

HighLife: Higher-arity Fact Harvesting

Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction

Position-aware Attention and Supervised Data Improve Slot Filling

Cross-Sentence N-ary Relation Extraction with Graph LSTMs

Systematic integration of biomedical knowledge prioritizes drugs for repurposing

Distant Supervision for Relation Extraction beyond the Sentence Boundary

BioCreative V CDR task corpus: a resource for chemical disease relation extraction

Relation Classification via Convolutional Deep Neural Network

The DDI corpus: An annotated corpus with pharmacological substances and drug-drug interactions

Constructing a semantic predication gold standard from the biomedical literature

The curation paradigm and application tool used for manual curation of the scientific literature at the Comparative Toxicogenomics Database

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals

Manual curation is not sufficient for annotation of genomic databases

Overview of DrugProt BioCreative VII track: quality evaluation and large scale text mining of drug-gene/protein relations

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations

Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)

Assessment of the second BioCreative PPI task : Automatic extraction of protein - protein interactions

Language Resource References

Chem-Di s: marker/mechanism Chem-Di s: therapeutic

Chem-Gene: expression -affects Chem-Gene: expression -decreases Chem-Gene: expression -increases Chem-Gene: localization -affects

feed-A: Don’t record investigated or motivating relationships that remain unknown and hypothetical

Field of Study

Computer Science

Venue Information

Name

International Conference on Language Resources and Evaluation

Type

conference

URL

http://www.lrec-conf.org/

Alternate Names

LREC
Int Conf Lang Resour Evaluation