Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 17, 2026

A Web Tool for Generating High Quality Machine-readable Biological Pathways

A Web Tool for Generating High Quality Machine-readable Biological Pathways

Published on: February 8, 2017

Benchmarking natural-language parsers for biological applications using dependency graphs.

Andrew B Clegg¹, Adrian J Shepherd

¹School of Crystallography, Birkbeck, University of London, Malet Street, London WC1E 7HX, UK. a.clegg@mail.cryst.bbk.ac.uk

BMC Bioinformatics

|January 27, 2007

Summary

Evaluating natural language processing parsers for biology using dependency graphs improves accuracy assessment. This method tailors evaluations to specific biological applications, highlighting crucial errors while minimizing minor linguistic variations.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Germline immunoglobulin genes: disease susceptibility genes hidden in plain sight?

Current opinion in systems biology·2023

Same author

Evolutionary remodelling of N-terminal domain loops fine-tunes SARS-CoV-2 spike.

EMBO reports·2022

Same author

An entropic safety catch controls hepatitis C virus entry and antibody resistance.

eLife·2022

Same author

Mechanistic diversity in MHC class I antigen recognition.

The Biochemical journal·2021

Same author

Characterization of the MurT/GatD complex in <i>Mycobacterium tuberculosis</i> towards validating a novel anti-tubercular drug target.

JAC-antimicrobial resistance·2021

Same author

Cholesterol sensing by CD81 is important for hepatitis C virus entry.

The Journal of biological chemistry·2020

Area of Science:

Bioinformatics
Computational Biology
Natural Language Processing

Background:

Assessing syntactic parsers in biology is challenging due to linguistic variations.
A novel evaluation method using dependency graphs is proposed.
This approach simplifies semantic relationship extraction for information retrieval.

Purpose of the Study:

To introduce a robust method for evaluating syntactic parser accuracy in biological contexts.
To demonstrate the adaptability of the evaluation method for application-specific criteria.

Main Methods:

Utilized the GENIA corpus as a gold standard for evaluation.
Tested four open-source parsers commonly used in bioinformatics.
Focused on Charniak-Lease and Bikel parsers for detailed subtask analysis.

More Related Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Jul 17, 2026

A Web Tool for Generating High Quality Machine-readable Biological Pathways

A Web Tool for Generating High Quality Machine-readable Biological Pathways

Published on: February 8, 2017

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Main Results:

The Charniak-Lease and Bikel parsers demonstrated superior performance.
Achieved accuracy comparable to or exceeding native dependency parsers in similar biological tasks.
The evaluation method effectively filtered out insignificant linguistic differences.

Conclusions:

Dependency graph evaluation enhances parser testing for biological applications.
This method accurately identifies critical errors and simplifies performance assessment.
Generated dependency graphs provide access to detailed syntax trees for advanced NLP techniques.