TY  - CONF
N2  - This paper presents in detail a linguistics study of a journalistic corpus of Malay describing Indonesian terrorism. The initial raw text was manually annotated for its parts-of-speech. It is the first corpus of its nature ever established in Malaysia. The objective of this research is to conduct an empirical analysis of the actual patterns of use in journalistic texts. This paper presents the characteristics of Malay terrorism corpus which include the properties, word classes, named entities and word occurrences. The results of this work are given purely in terms of the characteristics of a Malay terrorism corpus. The results are highly useful for solving larger tasks in the Natural Language Processing area, such as Information Retrieval and Information Extraction, in the area of terrorism. © 2012 IEEE.
N1  - cited By 1; Conference of 2012 1st IEEE Conference on Control, Systems and Industrial Informatics, ICCSII 2012 ; Conference Date: 23 September 2012 Through 26 September 2012; Conference Code:96023
ID  - scholars2476
TI  - Characteristics of a Malay journalistic corpus
SP  - 214
KW  - corpus; Empirical analysis; Information Extraction; Linguistic patterns; Malaysia; Named entities; NAtural language processing; word distribution
KW  -  Natural language processing systems; Terrorism
KW  -  Linguistics
CY  - Bandung
AV  - none
A1  - Zamin, N.
A1  - Oxley, A.
A1  - Bakar, Z.A.
A1  - Farhan, S.A.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84875103783&doi=10.1109%2fCCSII.2012.6470503&partnerID=40&md5=6776ad8b5bae336d40307290eb6d1aff
EP  - 218
Y1  - 2012///
SN  - 9781467310239
ER  -