Search in the Catalogues and Directories

Hits 1 – 1 of 1

1	Reducing VSM data sparseness by generalizing contexts: application to health text mining
	Périnet, Amandine; Hamon, Thierry
	In: International Workshop on Health Text Mining and Information Analysis ; https://hal.archives-ouvertes.fr/hal-01972762 ; International Workshop on Health Text Mining and Information Analysis, Jan 2014, Gothenburg, Sweden (2014)
	Abstract: International audience ; Vector Space Models are limited with low frequency words due to few available contexts and data sparseness. To tackle this problem, we generalize contexts by integrating semantic relations acquired with linguistic approaches. We use three methods that acquire hypernymy relations on a EHR corpus. Context Generalization obtains the best results when performed with hypernyms, the quality of the relations being more important than the quantity.
	Keyword: [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO]Computer Science [cs]; EHR corpus; hypernymy; Natural Language Processing; Specialized texts; Vector Space Models
	URL: https://hal.archives-ouvertes.fr/hal-01972762
	BASE
	Hide details