Converting BioProp Annotations to PASBio
Author Information
Author(s): Richard Tzong-Han Tsai, Hong-Jie Dai, Chi-Hsin Huang, Wen-Lian Hsu
Primary Institution: Yuan Ze University, Academia Sinica, National Tsing-Hua University
Hypothesis
We aim to build a system to convert BIOSMILE's BioProp annotation output to PASBio annotation.
Conclusion
Our approach allows PAS conversion between BioProp and PASBio annotation using BIOSMILE alongside our newly developed semi-automatic rule generator and rule-based converter.
Supporting Evidence
- The rule-based converter achieved an F-score of 85.29%.
- The combined system achieved an F-score of 69.08% for PASBio's 29 verbs.
- The study constructed a biomedical corpus based on the PropBank standard called BioProp.
Takeaway
This study created a tool that helps convert one type of scientific text annotation to another, making it easier for researchers to analyze biomedical literature.
Methodology
The study used named entity tagging, semantic role labeling, and a rule-based conversion approach.
Limitations
The performance may be affected by the absence of key terms for argument disambiguation and coordination ambiguity.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website