MI5 and CPNI desk officers need help to cope with volumes of intelligence and surveillance data: text analytics, data fusion and visual analytics.

1
CORPUS LINGUISTICS
School of Computing FACULTY OF ENGINEERING
Eric Atwell, Nora Abbas, Amal Al-Saif, Claire
Brierley, Kais Dukes, Katja Markert, Andrew
McKinlay, Owen Nancarrow, Majdi Sawalha,
Abdul-Baquee Sharaf, Fangzhong Su, Josiah Wang,
Justin Washtell http//www.comp.leeds.ac.uk/nlp
http//www.comp.leeds.ac.uk/arabic
ARABIC NLP
SEARCH the QURAN
MAKING SENSE
TEXT ANALYTICS
MI5 and CPNI desk officers need help to cope with
volumes of intelligence and surveillance data
text analytics, data fusion and visual analytics.
Language research in Computing is also known as
Text Analytics, Natural Language Processing,
Computational Linguistics, or Language
Engineering. Computational modelling of language
requires a CORPUS, a sample of text. Our research
at Leeds University focusses on bootstrapping
linguistic knowledge and resources from text for
example ProPOSEL, a Prosody and Part-Of-Speech
English Lexicon
Arabic has a challenging script, and complex
word-structure and grammar
Find key words, concepts, topics. Arabic and 8
English translations to improve precision and
recall

What is Corpus Linguistics? key concepts from
Proc Int Conf Corpus Linguistics 2003, 05, 07, 09
(Rayson and Mariani 2009)
Body text
References Brierley C, Atwell E. 2008. ProPOSEL
A prosody and POS English lexicon for language
engineering. Proc LREC'08 Sawalha M, Atwell E.
2008. Comparative evaluation of Arabic language
morphological analysers and stemmers. Proc
COLING08 Atwell E et al. 2008. Mapping Middle
Eastern and North African diasporas Arabic
corpus linguistics research at the University of
Leeds. Proc BRISMES08 Dukes K. 2009. The
Crescent Quran Corpus. http//quran.uk.net/
Rayson P, Mariani J. 2009. Visualising Corpus
Linguistics. Proc CL09