Using Anaphora Resolution in Myanmar Summaries

Abstract

Automatic summarization is the process of reducing a text document with a computer program. A summary retains the most important points of the original document. It is essential for Natural Language Processing (NLP) researches. Automatically summarized text can sometimes result in broken anaphoric references. This is due to the fact that the sentences are extracted without making any deeper linguistic analysis of the text. Anaphoric reference resolution is a common phenomenon in natural language processing, which has correspondingly received a significant amount of attention in the literature. In this paper, we present a Myanmar Pronominal Anaphora Resolution (MPAR) algorithm which bases on Hobbs’ (1986) algorithm that works on only the surface syntax of sentences in a given text. This paper also proposes a new summarization method using MPAR algorithm for Myanmar texts. The summarized text using anaphora resolution can achieves more meaningful result than a system not using anaphora resolution.