Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Bidirectional incremental parsing for automatic pathway identification with combinatory categorial grammar.

J C Park1, H S Kim, J J Kim

  • 1Computer Science Department and Advanced Information Technology Research Center, Korea Advanced Institute of Science and Technology (KAIST), 373-1 Kusong-dong, Yusong-gu, Daejon 305-701 South Korea. park@nlp.kaist.ac.kr

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|March 27, 2001
PubMed
Summary

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

Engineering the thermostable D-hydantoinases from two thermophilic Bacilli based on their primary structures.

Annals of the New York Academy of Sciences·1999
Same author

Biochemical properties of thermostable D-hydantoinase from Bacillus thermocatenulatus GH-2.

Annals of the New York Academy of Sciences·1999
Same author

A cultivation strategy of recombinant Escherichia coli for mass production of thermostable D-hydantoinase.

Annals of the New York Academy of Sciences·1999
Same author

Assignment of the human cts18.1 gene PSCD2L to chromosome 19 band q13 using a radiation hybrid mapping panel.

Cytogenetics and cell genetics·1999
Same author

Human DXYS156 of pentanucleotide repeat (TAAAA)n: chromosomal localization by somatic hybrid mapping and sequencing analysis.

Cytogenetics and cell genetics·1999
Same author

Assignment1 of the human basic fibroblast growth factor gene FGF2 to chromosome 4 band q26 by radiation hybrid mapping.

Cytogenetics and cell genetics·1999

This study presents a novel natural language processing system for extracting protein-protein interactions from biomedical texts. The system uses combinatory categorical grammar for more accurate syntactic analysis, achieving encouraging results on Medline abstracts.

Area of Science:

  • Biomedical Informatics
  • Computational Linguistics

Background:

  • Automated extraction of protein-protein interactions (PPIs) from biomedical literature is crucial for biological research.
  • Existing natural language processing (NLP) methods often oversimplify syntactic analysis for efficiency.

Purpose of the Study:

  • To develop and evaluate an NLP system for accurate extraction of PPI assertions.
  • To address limitations in syntactic analysis found in previous PPI extraction systems.

Main Methods:

  • Implementation of a system utilizing combinatory categorical grammar (CCG).
  • Incorporation of a controlled bidirectional and incremental parsing mechanism.
  • Evaluation on a large dataset of Medline abstracts.

Main Results:

Related Experiment Videos

  • The system demonstrates competence in modeling natural language syntax for PPI extraction.
  • Encouraging performance metrics were achieved on the Medline abstract dataset.
  • The bidirectional and incremental parsing approach proved effective.

Conclusions:

  • The developed CCG-based system offers a more robust approach to NLP for biomedical text analysis.
  • This system advances the field of automated information extraction for protein-protein interactions.
  • Future work may involve further refinement and application to broader biomedical corpora.