Cover Image

Comparison of Different Orthographies for Machine Translation of Under-Resourced Dravidian Languages

Main Authors: Bharathi Raja Chakravarthi, Mihael Arcan, John P. McCrae
Format: Proceeding
Bahasa: eng
Terbitan: , 2019
Online Access: https://zenodo.org/record/3266918
ctrlnum 3266918
fullrecord <?xml version="1.0"?> <dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><creator>Bharathi Raja Chakravarthi</creator><creator>Mihael Arcan</creator><creator>John P. McCrae</creator><date>2019-05-20</date><description>Under-resourced languages are a significant challenge for statistical approaches to machine translation, and recently it has been shown that the usage of training data from closely-related languages can improve machine translation quality of these languages. While languages within the same language family share many properties, many under-resourced languages are written in their own native script, which makes taking advantage of these language similarities difficult. In this paper, we propose to alleviate the problem of different scripts by transcribing the native script into common representation i.e. the Latin script or the International Phonetic Alphabet (IPA). In particular, we compare the difference between coarse-grained transliteration to the Latin script and fine-grained IPA transliteration. We performed experiments on the language pairs English-Tamil, English-Telugu, and English-Kannada translation task. Our results show improvements in terms of the BLEU, METEOR and chrF scores from transliteration and we find that the transliteration into the Latin script outperforms the fine-grained IPA transcription.</description><identifier>https://zenodo.org/record/3266918</identifier><identifier>10.4230/OASIcs.LDK.2019.6</identifier><identifier>oai:zenodo.org:3266918</identifier><language>eng</language><relation>info:eu-repo/grantAgreement/EC/H2020/731015/</relation><rights>info:eu-repo/semantics/openAccess</rights><rights>https://creativecommons.org/licenses/by/4.0/legalcode</rights><title>Comparison of Different Orthographies for Machine Translation of Under-Resourced Dravidian Languages</title><type>Journal:Proceeding</type><type>Journal:Proceeding</type><recordID>3266918</recordID></dc>
language eng
format Journal:Proceeding
Journal
author Bharathi Raja Chakravarthi
Mihael Arcan
John P. McCrae
title Comparison of Different Orthographies for Machine Translation of Under-Resourced Dravidian Languages
publishDate 2019
url https://zenodo.org/record/3266918
contents Under-resourced languages are a significant challenge for statistical approaches to machine translation, and recently it has been shown that the usage of training data from closely-related languages can improve machine translation quality of these languages. While languages within the same language family share many properties, many under-resourced languages are written in their own native script, which makes taking advantage of these language similarities difficult. In this paper, we propose to alleviate the problem of different scripts by transcribing the native script into common representation i.e. the Latin script or the International Phonetic Alphabet (IPA). In particular, we compare the difference between coarse-grained transliteration to the Latin script and fine-grained IPA transliteration. We performed experiments on the language pairs English-Tamil, English-Telugu, and English-Kannada translation task. Our results show improvements in terms of the BLEU, METEOR and chrF scores from transliteration and we find that the transliteration into the Latin script outperforms the fine-grained IPA transcription.
id IOS16997.3266918
institution DEFAULT
institution_type library:public
library
library DEFAULT
collection DEFAULT
city DEFAULT
province DEFAULT
repoId IOS16997
first_indexed 2022-06-06T03:23:40Z
last_indexed 2022-06-06T03:23:40Z
recordtype dc
merged_child_boolean 1
_version_ 1739475830575202304
score 17.204899

Lihat Juga