Anaphora Resolution for Myanmar Text Using K-Nearest Neighbor Algorithm

Abstract

Anaphora resolution which most common ly appears as pronoun resolution is the problem of resolving references to earlier or later items in the discourse. Anaphora resolution is an active area of research, such as text min ing, text su mmarization, dialogue interpretations, information extraction, and so on. Anaphora resolution in English and other European languages has been well done in early. But Myanmar Language has not sufficiently applied. This paper presents Myanmar anaphora resolution system by using rule-based part of speech tagging and machine learning approach. Rule-based manner with morphological informat ion is used to collect anaphora and possible antecedents. K-Nearest Neighbor (k-NN) approach is used to select the most probable candidate as the antecedent of the anaphor.