Title :
Construction of compound nouns (CNs) for noun phrase in Malay sentence
Author :
Rahman, Suhaimi Ab ; Omar, Nazlia ; Hassan, Noor Baizura Che
Author_Institution :
Software Eng. Dept., Univ. Tenaga Nasional, Kajang, Malaysia
Abstract :
This paper addresses the process of compound noun construction from simple Malay sentences. To construct the compound noun, we characterize them according to the noun phrase categories in Malay sentence. All these categories are formed based on the combination of noun and noun, noun and noun modifier and noun and non-noun modifier. The noun phrase in Malay sentence is referred to as a word group with a noun as its head. The head noun is then accompanied by modifiers or compliments. The modifiers or compliments can be either noun, verb, adjective, determiner or etc. A good understanding of Malay language is an important skill for evaluating and nominating a correct compound noun found from the data collection. The compound noun then will be match with its appropriate category. We also design a general process flow to show the steps involved in creating compound noun from our data collection. The total number of compound nouns collected is important, so that the searching process becomes more widespread. A suitable searching method and data representation is also significant for handling compound nouns from a database.
Keywords :
grammars; natural languages; word processing; CN; Malay language; Malay sentences; compound noun construction; data collection; data representation; head noun; noun compliments; noun phrase categories; noun-nonnoun modifier category; noun-noun category; noun-noun modifier category; searching process; word group; Books; Compounds; Context; Databases; Educational institutions; Speech; Syntactics; Compound noun; noun phrase category; noun phrase frame structure; parts of speech(POS);
Conference_Titel :
Information Retrieval & Knowledge Management (CAMP), 2012 International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4673-1091-8
DOI :
10.1109/InfRKM.2012.6204976