Noun-Noun Metaphor Identification in Myanmar Language

Abstract

Figurative languages can be found in all areas of human activities, literary, discourse and conversation. Metaphor, which is one of the figurative languages, becomes a problem in natural language processing (NLP). In Myanmar language, there is a gap for specific work of metaphor in NLP research field. This paper presents about the identification of noun-noun metaphor by using Myanmar WordNet (MMWN) and additional resources, such as wordnet2sql, bilingual dictionary and compound noun corpus. In this work, step by step processing of noun-noun metaphor identification are explained in details. Sentences are used for the experiments and categorized in five domains. Semantic relations in the WordNets are used for metaphor identification (MI) and compound noun corpus is used to identified the literal usage. The experimental results of noun pairs extraction and metaphor identification are described in this paper. The precisions are 57% in News, 76% in Novels, 79% in Articles, 81% in Formal and 76% in Conversational sentences. The issues found in metaphor identification and overall discussion about these issues are also presented in this paper.