ŘEHŮŘEK, Radim. Text Segmentation Using Context Overlap. Progress in Artificial Intelligence. Guimarães, Portugal: Springer Berlin / Heidelberg, 2007, vol. 2007, No 4874, p. 647-658, 11 pp. ISSN 0302-9743. |
Other formats:
BibTeX
LaTeX
RIS
@article{745015, author = {Řehůřek, Radim}, article_location = {Guimarães, Portugal}, article_number = {4874}, keywords = {text segmentation; LSI; latent semantic indexing}, language = {eng}, issn = {0302-9743}, journal = {Progress in Artificial Intelligence}, title = {Text Segmentation Using Context Overlap}, url = {http://www.springerlink.com/content/k820g107h7067383/?p=9cc314a6a70b4ca286722b609e097494&pi=0}, volume = {2007}, year = {2007} }
TY - JOUR ID - 745015 AU - Řehůřek, Radim PY - 2007 TI - Text Segmentation Using Context Overlap JF - Progress in Artificial Intelligence VL - 2007 IS - 4874 SP - 647-658 EP - 647-658 PB - Springer Berlin / Heidelberg SN - 03029743 KW - text segmentation KW - LSI KW - latent semantic indexing UR - http://www.springerlink.com/content/k820g107h7067383/?p=9cc314a6a70b4ca286722b609e097494&pi=0 N2 - In this paper we propose features desirable of linear text segmentation algorithms for the Information Retrieval domain, with emphasis on improving high similarity search of heterogeneous texts. We proceed to describe a robust purely statistical method, based on context overlap exploitation, that exhibits these desired features. Experimental results are presented, along with comparison to other existing algorithms. ER -
ŘEHŮŘEK, Radim. Text Segmentation Using Context Overlap. \textit{Progress in Artificial Intelligence}. Guimarães, Portugal: Springer Berlin / Heidelberg, 2007, vol.~2007, No~4874, p.~647-658, 11 pp. ISSN~0302-9743.
|