Segmentation of texts and biological sequences into lexical and structural units using a machine-learning approach

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Authors	HUDÍK Tomáš LEXA Matej
Year of publication	2005
Type	Article in Proceedings
Conference	Proceedings of the 1st International Summer School on Computational Biology
MU Faculty or unit	Faculty of Informatics
Citation
Web	http://www.cba.muni.cz/summer-school2005/index.php
Field	Informatics
Keywords	machine learning ; segmentation; I-sites
Description	Results demonstrate that segmentation problems in the linguistic domain and protein sequence domain are similar and can be treated with similar computational tools. From our point of view protein sequences contain segments that are analogical to words in natural language.
Related projects:	Human-computer interaction, dialog systems and assistive technologies