Abstract
This paper addresses the process of transforming the noun phrase structure form into a list of rules to detect compound noun words in Malay sentences. Rules are collection of word syntax that are derived from a specific resource (as defined in our study). Comprehension of the concept rule used in a system is important (i.e. using rules to find a list of compound nouns that may exist in a sentence). The noun phrase frame structure is a form that contains a list of noun modifier categories. The list of noun modifier categories is then divided into several sub-categories such as numeral, numeral classifier, appellation, etc. All categories are arranged in sequence based on correct grammar. The noun phrase frame structure is then used to analyse the sentence. The words in the sentence will be arranged according to their suitable noun modifier category as defined by the noun phrase frame structure. In terms of data requirements, we will only focus on examples of sentences that combine two noun phrases.
Highlights
Recent research on Natural Language Processing (NLP) has been constantly growing, where one research area in text processing has been identified as a potential research which can be used to manage open text in detecting a set of compound nouns retrieved from a sentence
This paper does not discuss any evaluation of test results to measure the accuracy of the results of compound nouns
The fundamental concept of noun phrase was discussed in which a detailed review of compound nouns in Malay sentences was performed
Summary
Recent research on Natural Language Processing (NLP) has been constantly growing, where one research area in text processing has been identified as. The detection of compound nouns in a sentence is useful for the development of NLP application systems such as the detection of heads and modifiers in sentences, language translation systems, text summarization, word categorization, etc. This research work only focuses on the detection of compound nouns in Malay sentences. These sentences comprise a combination of two noun phrases known as ‘subject and predicate’. We developed a system to transfer all the words from a text files into a database. Another system was developed to assist in accelerating the process of data preparation and compilation
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have