Abstract: This article aims to present the results of clustering in documents, extracted from Internet and related to compositional phrasemes (pragmatemes). We are studying conditions (situation, context), which can stipulate presence of these units in a text. Pragmateme’s structure and functioning particularities are taken into consideration. An important objective of the work is selection of an adequate algorithm for tag extraction and clustering, so that we can further compare and apply the results, obtained for different languages.

Keywords: pragmateme, compositional phraseme, tag extraction, clustering analysis

ACM Classification Keywords: I.2.7. Natural Language Processing

Link:

AUTOMATED TAG EXTRACTION & CLUSTERING IN DOCUMENTS CONTAINING COMPOSITIONAL PHRASEMES

Vera Danilova, Xavier Blanco, Dmitry Stefanovskiy

http://foibg.com/ibs_isc/ibs-27/ibs-27-p13.pdf