2016 | OriginalPaper | Chapter
A Sematic Role Labeling Approach in Myanmar Text
Authors : May Thu Naing, Aye Thida
Published in: Genetic and Evolutionary Computing
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
There is a generally certainty in the natural language and computational linguistics communities that semantic role labeling (SRL) is an important step toward improving significant applications, e.g. question answering, text summarization and information extraction. We propose a new method for assigning semantic roles on the structured trees of Myanmar sentences using Myanmar Verb Frame (MVF). In this paper, there is not use any machine learning techniques for SRL. It employs with predicate-argument identification algorithm and mapping algorithm to identify semantic roles in Myanmar. These algorithms mainly work on the syntax structure of Myanmar sentences. This system achieves over 70 % success rate in labeling the semantic role of pre-segmented constituents on the datasets.