Unsupervised Dependency Corpus Annotation for Myanmar Language
Citations Over Time
Abstract
Dependency parsing can provide the connection of linguistic unit (words) by a directed links. This paper presents annotating a general domain corpus by using unsupervised approach by applying Universal part-of-speech (U-POS) to build Treebank for unsupervised dependency parsing of Myanmar Language. Up to now it is still hard task to obtain complete syntactic structures for Myanmar Language. Dependency structures of words in Myanmar sentences are also presented of general words and phrases orders and the relations of basic sentence structures. To annotate by using U-POS, UDPipe is used. Moreover, the preliminary results of annotated trees and parsing experiment are presented. Parsing experiments are evaluated by UDPipe in terms of unlabeled and labeled attachment scores: (UAS) and (LAS), which are 93.20%, and 91.21% in test experiment respectively.
Related Papers
- → Comparing State-of-the-art Dependency Parsers on the Italian Stanford Dependency Treebank(2016)8 cited
- An Empirical Evaluation of Automatic Conversion from Constituency to Dependency in Hungarian(2014)
- → A preliminary comparison of state-of-the-art dependency parsers on the Italian Stanford Dependency Treebank(2014)3 cited
- → Factors influencing dependency parsing of coordinating structure(2009)1 cited
- → Concurrent Parsing of Constituency and Dependency(2019)