Search research articles

Search research articles

Related Experiment Videos

Defining and relating biomedical terms: towards a cross-language morphosemantics-based system.

Fiammetta Namer¹, Robert Baud

¹UMR 7118 ATILF & Université Nancy2, CLSH, 23 Boulevard Albert 1er, BP3397, 54015 Nancy Cedex, France. fiammetta.namer@univ-nancy2.fr

International Journal of Medical Informatics

|July 4, 2006

Summary

This summary is machine-generated.

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

Towards a Terminologia Anatomica Humana.

Anatomical science international·2024

Same author

The Representation of White Matter in the Central Nervous System.

Frontiers in neuroanatomy·2019

Same author

Ordering by the numbers in anatomy and by letters Too.

Clinical anatomy (New York, N.Y.)·2017

Same author

Human anatomy nomenclature rules for the computer age.

Clinical anatomy (New York, N.Y.)·2016

Same author

The development of CCAM: the new French coding system of clinical procedures.

Health information management : journal of the Health Information Management Association of Australia·2009

Same author

Morphosemantic parsing of medical compound words: transferring a French analyzer to English.

International journal of medical informatics·2008

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

This study introduces a system for automatically assigning semantic information to biomedical terms, creating multilingual lexical networks. The morphosemantic approach successfully groups terms by synonymy, hyponymy, and proximity.

Area of Science:

Computational linguistics
Bioinformatics
Lexicography

Background:

Automatic assignment of semantic information to compound terms is essential for multilingual databases and cross-language information retrieval.
Morphosemantics offers a promising approach for building multilingual lexical networks within biomedical corpora.

Purpose of the Study:

To present a system for automatically assigning definitions and semantic relations (synonymy, hyponymy, proximity) to biomedical terms.
To demonstrate the utility of morphosemantics in constructing multilingual lexical networks.

Main Methods:

Integration of a language-specific morphosemantic parser.
Utilization of a multilingual table for basic word root relations.
Application of language-independent rules for generating related terms.

Related Experiment Videos

Main Results:

The system was implemented for French, processing a 29,000-term biomedical lexicon.
Over 3000 lexical families were generated.
Results were validated against expert-annotated data.

Conclusions:

The proposed morphosemantic approach effectively automates the assignment of semantic information to biomedical terms.
This method facilitates the creation of robust multilingual lexical networks for biomedical applications.
The system demonstrates high performance and accuracy in grouping related terms.