Development of the lexico-conceptual knowledge resource for Myanmar NLP applications

Abstract

The computational lexicons and semantic resources as WordNets of knowledge resources are mostly important for Natural Language Processing (NLP). The importance of computational lexicon is even greater in languages with rich morphology, where the lexicon is expected to provide morphological analyzers with enough information to enable them to correctly process intricately inflected forms. This paper presents for the semiautomatic construction of a multipurpose lexico-conceptual knowledge resources for NLP systems by acquiring the lexical and conceptual knowledge from WordNet and Myanmar<->English Machine Readable Dictionaries (MRDs). To construct the WordNet like lexicon, to collect the translation links, semantic meaning and synset links, the existing bilingual MRDs and English WordNet are used for building the knowledge resources. The collected of links and their meaning are manually verified. In addition, morphological processors (analyzers and generators) are support to handle cases of inflectional morphology. These resources are very efficient and effected for NLP applications, the building methodology of constructing Myanmar<->English Computational Lexicon and Myanmar WordNet lexical database reduced the human effort and time consuming.