Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy
A lexicon is the source of specific knowledge about individual words in the language which also known as the heart of language processing system. This research will focus on construction of a computational lexicon model for Malay Language that involved computational study of the form and behaviour o...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | English |
Published: |
2016
|
Online Access: | https://ir.uitm.edu.my/id/eprint/17764/2/TM_HARSHIDA%20HASMY%20CS%2016_5.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-uitm-ir.17764 |
---|---|
record_format |
uketd_dc |
spelling |
my-uitm-ir.177642019-02-06T07:29:15Z Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy 2016 Hasmy, Harshida A lexicon is the source of specific knowledge about individual words in the language which also known as the heart of language processing system. This research will focus on construction of a computational lexicon model for Malay Language that involved computational study of the form and behaviour of words. This research also includes study on morphological arrangement of Malay affixation process which includes prefixes, suffixes, circumfixes and infixes with the intention of constructing a collection of new Malay lexicons that will be automatically constructed from a single root word. This research conducted experiments on 2101 root words found in the Malay translated Quranic documents. The words then experimented with Malay affixation rules using the affixed words analyser. Numerous new words are constructed from a single root word with the word classes using the affixed words analyser by adding 52 affixes rules which consists of 20 prefixes, 3 suffixes, 25 circumfixes, and 4 infixes to the root word. Nevertheless, proper names need to be extracted from the list and this is done by recognising and removing particular name entities. Finally, each new word is then compared with current Malay dictionary to ensure whether the word generated is currently being used or it is a new generated new word. Results from this analysis open opportunity to construct new Malay word variant to enrich the Malay lexicon and may help to support more efficient method for any related Malay language computer linguistic analysis particularly any research on Malay Quranic translation documents. 2016 Thesis https://ir.uitm.edu.my/id/eprint/17764/ https://ir.uitm.edu.my/id/eprint/17764/2/TM_HARSHIDA%20HASMY%20CS%2016_5.pdf text en public mphil masters Universiti Teknologi MARA Faculty of Computer and Mathematical Sciences |
institution |
Universiti Teknologi MARA |
collection |
UiTM Institutional Repository |
language |
English |
description |
A lexicon is the source of specific knowledge about individual words in the language which also known as the heart of language processing system. This research will focus on construction of a computational lexicon model for Malay Language that involved computational study of the form and behaviour of words. This research also includes study on morphological arrangement of Malay affixation process which includes prefixes, suffixes, circumfixes and infixes with the intention of constructing a collection of new Malay lexicons that will be automatically constructed from a single root word. This research conducted experiments on 2101 root words found in the Malay translated Quranic documents. The words then experimented with Malay affixation rules using the affixed words analyser. Numerous new words are constructed from a single root word with the word classes using the affixed words analyser by adding 52 affixes rules which consists of 20 prefixes, 3 suffixes, 25 circumfixes, and 4 infixes to the root word. Nevertheless, proper names need to be extracted from the list and this is done by recognising and removing particular name entities. Finally, each new word is then compared with current Malay dictionary to ensure whether the word generated is currently being used or it is a new generated new word. Results from this analysis open opportunity to construct new Malay word variant to enrich the Malay lexicon and may help to support more efficient method for any related Malay language computer linguistic analysis particularly any research on Malay Quranic translation documents. |
format |
Thesis |
qualification_name |
Master of Philosophy (M.Phil.) |
qualification_level |
Master's degree |
author |
Hasmy, Harshida |
spellingShingle |
Hasmy, Harshida Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy |
author_facet |
Hasmy, Harshida |
author_sort |
Hasmy, Harshida |
title |
Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy |
title_short |
Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy |
title_full |
Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy |
title_fullStr |
Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy |
title_full_unstemmed |
Construction model of new Malay language lexicons using morphological affixed rules / Harshida Hasmy |
title_sort |
construction model of new malay language lexicons using morphological affixed rules / harshida hasmy |
granting_institution |
Universiti Teknologi MARA |
granting_department |
Faculty of Computer and Mathematical Sciences |
publishDate |
2016 |
url |
https://ir.uitm.edu.my/id/eprint/17764/2/TM_HARSHIDA%20HASMY%20CS%2016_5.pdf |
_version_ |
1783733593988661248 |