Page 118 - Conference Book The 3rd IConVET "Future of TVET Graduates: Developing Talent for Industry 4.0 and The New Normal"

The 3 International Conference
rd
on Vocational Education and Technology (IConVET)
Universitas Pendidikan Ganesha - Bali | 7 November, 2020
th
A MODEL FOR POST TRANSLITERATION
SUGGESTION FOR BALINESE PALM LEAF
MANUSCRIPT WITH TEXT GENERATION AND LSTM
MODEL

Made Windu Antara Kesiman, I Made Dendi Maysanjaya

Virtual Vision, Image, and Pattern Research Group (VVIP-RG)
Faculty of Engineering and Vocational, Universitas Pendidikan Ganesha

Corresponding author: antara.kesiman@undiksha.ac.id

Abstract. The main challenge found in building an automatic transliteration
system for Balinese palm leaf manuscript (Lontar) collections is that the
recognition error in a small portion of glyphs of Balinese script can affect
the results of transliteration widely. This is due to the fundamental nature of
Balinese script which is a complex alphasyllabic script. This paper presents
an initial proposition for a general scheme and model for suggesting several
possible transliterations with text generation and LSTM for Lontar
collection. The Edit-Insert-Replace model was proposed to be applied on the
existing word collection dataset and a Bidirectional LSTM model with
specific feature extraction method was built for the training process of post
transliteration suggestion module. This module will help in suggesting
several possible transliterations based on the initial transliteration from the
previous system.

| IConVET 2020 | 118

https://conference.undiksha.ac.id/iconvet/ | 118 |