Related Experiment Video
Updated: May 2, 2026

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
Published on: February 23, 2019
Annotated corpus for traditional formula-disease relationships in biomedical articles
Sangjun Yea1, Ho Jang2,3, Soyoung Kim2,3
1Korean medicine data division, Korea Institute of Oriental Medicine, Daejeon, 34054, Republic of Korea. tomita@kiom.re.kr.
This study introduces the Traditional Formula-Disease Relationship (TFDR) corpus, a new dataset for NLP. It aids in extracting knowledge on traditional formulas and diseases from biomedical literature.
Area of Science:
- Biomedical Informatics
- Traditional Medicine
- Natural Language Processing
Background:
- Traditional Formulas (TF) are gaining global recognition as alternative medicine.
- Extracting knowledge on TF-disease relationships from literature is challenging manually.
- Natural Language Processing (NLP) offers potential for automated knowledge extraction.
Purpose of the Study:
- To introduce the Traditional Formula-Disease Relationship (TFDR) corpus.
- To facilitate automatic extraction of TF-disease relationships using NLP.
- To address the lack of high-quality annotated data in traditional medicine research.
Main Methods:
- Developed a manually annotated corpus (TFDR) from 740 PubMed abstracts.
- Included mentions of Traditional Formulas (TF) and diseases.
- Annotated 1,109 TF-disease relationships within 744 key-sentences.
Main Results:
- The TFDR corpus contains 6,211 TF mentions and 7,166 disease mentions.
- Successfully captured 1,109 relationships between TFs and diseases.
- Provides a valuable resource for NLP applications in traditional medicine.
Conclusions:
- The TFDR corpus is a crucial resource for advancing NLP in traditional medicine.
- Enables automated knowledge discovery of TF-disease interactions.
- Supports integration of traditional medicine insights into biomedical science.
Related Concept Videos
Dose-Response Relationship: Overview
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Factors Influencing Drug Absorption: Disease States and Pharmacology
Substances such as alcohol and specific drugs, including antineoplastics, can also negatively impact drug absorption. For instance,...
Dosage Regimen: Individualization
Drug Dosing: Obese Patients
Hazard Ratio
For example, in a clinical trial...

