Title: Improved Word Alignment System for Myanmar-English Machine Translation
Abstract: Word alignment is an essential task for every Statistical Machine Translation (SMT) system. An alignment is the arrangement of two or more alignments between the parallel sentences. The problem of word alignment in SMT is to find the strong alignment in the corresponding sentence pairs. Moreover, popular word alignment system (GIZA++) needs improvement in Myanmar-English machine translation because Myanmar is inflected, and it is also a language scarce resource. For this reason, this paper presents the idea of word alignment system by adding the extra resources: word and Name Entity Recognition (NER) translation pairs to the existing training data to improve the word alignment system. Experimental results show that the proposed word alignment system reduces the Alignment Error Rate (AER) than baseline.
Publication Year: 2020
Publication Date: 2020-11-05
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 1
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot