@inproceedings{teferra-abate-etal-2018-parallel,
title = "Parallel Corpora for bi-Directional Statistical Machine Translation for Seven {E}thiopian Language Pairs",
author = "Teferra Abate, Solomon and
Melese, Michael and
Yifiru Tachbelie, Martha and
Meshesha, Million and
Atinafu, Solomon and
Mulugeta, Wondwossen and
Assabie, Yaregal and
Abera, Hafte and
Ephrem, Binyam and
Abebe, Tewodros and
Tsegaye, Wondimagegnhue and
Lemma, Amanuel and
Andargie, Tsegaye and
Shifaw, Seifedin",
editor = "Machonis, Peter and
Barreiro, Anabela and
Kocijan, Kristina and
Silberztein, Max",
booktitle = "Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3812",
pages = "83--90",
abstract = "In this paper, we describe the development of parallel corpora for Ethiopian Languages: Amharic, Tigrigna, Afan-Oromo, Wolaytta and Geez. To check the usability of all the corpora we conducted baseline bi-directional statistical machine translation (SMT) experiments for seven language pairs. The performance of the bi-directional SMT systems shows that all the corpora can be used for further investigations. We have also shown that the morphological complexity of the Ethio-Semitic languages has a negative impact on the performance of the SMT especially when they are target languages. Based on the results we obtained, we are currently working towards handling the morphological complexities to improve the performance of statistical machine translation among the Ethiopian languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="teferra-abate-etal-2018-parallel">
<titleInfo>
<title>Parallel Corpora for bi-Directional Statistical Machine Translation for Seven Ethiopian Language Pairs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Solomon</namePart>
<namePart type="family">Teferra Abate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Melese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Yifiru Tachbelie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Million</namePart>
<namePart type="family">Meshesha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solomon</namePart>
<namePart type="family">Atinafu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wondwossen</namePart>
<namePart type="family">Mulugeta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaregal</namePart>
<namePart type="family">Assabie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hafte</namePart>
<namePart type="family">Abera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyam</namePart>
<namePart type="family">Ephrem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tewodros</namePart>
<namePart type="family">Abebe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wondimagegnhue</namePart>
<namePart type="family">Tsegaye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanuel</namePart>
<namePart type="family">Lemma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsegaye</namePart>
<namePart type="family">Andargie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seifedin</namePart>
<namePart type="family">Shifaw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Machonis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anabela</namePart>
<namePart type="family">Barreiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Kocijan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Silberztein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe the development of parallel corpora for Ethiopian Languages: Amharic, Tigrigna, Afan-Oromo, Wolaytta and Geez. To check the usability of all the corpora we conducted baseline bi-directional statistical machine translation (SMT) experiments for seven language pairs. The performance of the bi-directional SMT systems shows that all the corpora can be used for further investigations. We have also shown that the morphological complexity of the Ethio-Semitic languages has a negative impact on the performance of the SMT especially when they are target languages. Based on the results we obtained, we are currently working towards handling the morphological complexities to improve the performance of statistical machine translation among the Ethiopian languages.</abstract>
<identifier type="citekey">teferra-abate-etal-2018-parallel</identifier>
<location>
<url>https://aclanthology.org/W18-3812</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>83</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Corpora for bi-Directional Statistical Machine Translation for Seven Ethiopian Language Pairs
%A Teferra Abate, Solomon
%A Melese, Michael
%A Yifiru Tachbelie, Martha
%A Meshesha, Million
%A Atinafu, Solomon
%A Mulugeta, Wondwossen
%A Assabie, Yaregal
%A Abera, Hafte
%A Ephrem, Binyam
%A Abebe, Tewodros
%A Tsegaye, Wondimagegnhue
%A Lemma, Amanuel
%A Andargie, Tsegaye
%A Shifaw, Seifedin
%Y Machonis, Peter
%Y Barreiro, Anabela
%Y Kocijan, Kristina
%Y Silberztein, Max
%S Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F teferra-abate-etal-2018-parallel
%X In this paper, we describe the development of parallel corpora for Ethiopian Languages: Amharic, Tigrigna, Afan-Oromo, Wolaytta and Geez. To check the usability of all the corpora we conducted baseline bi-directional statistical machine translation (SMT) experiments for seven language pairs. The performance of the bi-directional SMT systems shows that all the corpora can be used for further investigations. We have also shown that the morphological complexity of the Ethio-Semitic languages has a negative impact on the performance of the SMT especially when they are target languages. Based on the results we obtained, we are currently working towards handling the morphological complexities to improve the performance of statistical machine translation among the Ethiopian languages.
%U https://aclanthology.org/W18-3812
%P 83-90
Markdown (Informal)
[Parallel Corpora for bi-Directional Statistical Machine Translation for Seven Ethiopian Language Pairs](https://aclanthology.org/W18-3812) (Teferra Abate et al., LR4NLP 2018)
ACL
- Solomon Teferra Abate, Michael Melese, Martha Yifiru Tachbelie, Million Meshesha, Solomon Atinafu, Wondwossen Mulugeta, Yaregal Assabie, Hafte Abera, Binyam Ephrem, Tewodros Abebe, Wondimagegnhue Tsegaye, Amanuel Lemma, Tsegaye Andargie, and Seifedin Shifaw. 2018. Parallel Corpora for bi-Directional Statistical Machine Translation for Seven Ethiopian Language Pairs. In Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing, pages 83–90, Santa Fe, New Mexico, USA. Association for Computational Linguistics.