TY - CHAP

T1 - Business-Media Analysis for Information Extraction

AU - Pronoza, Ekaterina

AU - Yagunova, Elena

PY - 2013

Y1 - 2013

N2 - In this paper an approach to primary business-media analysis for further information extraction is proposed. We consider business events representation by looking into part of speech (POS) distribution across tagged n-grams. Two Russian business-media corpora, Russian Business Consulting (RBC) and Commersant, are analyzed, and it is shown that they differ not only in style or themes coverage but also in the range of contexts for the words which mark business-events. Purchase, merger and ownership events are given a closer look at, and it is shown that they are mostly represented by noun phrases in both corpora rather than verbal phrases.

AB - In this paper an approach to primary business-media analysis for further information extraction is proposed. We consider business events representation by looking into part of speech (POS) distribution across tagged n-grams. Two Russian business-media corpora, Russian Business Consulting (RBC) and Commersant, are analyzed, and it is shown that they differ not only in style or themes coverage but also in the range of contexts for the words which mark business-events. Purchase, merger and ownership events are given a closer look at, and it is shown that they are mostly represented by noun phrases in both corpora rather than verbal phrases.

KW - Information extraction

KW - business media

M3 - Article in an anthology

SN - ISSN: 1870-4069

SP - 103

EP - 114

BT - Research in Computing Science: Advances in Soft Computing Techniques

ER -