@inproceedings{yadav-shrivastava-2021-a3,
title = "A3-108 Machine Translation System for {L}o{R}es{MT} Shared Task @{MT} Summit 2021 Conference",
author = "Yadav, Saumitra and
Shrivastava, Manish",
editor = "Ortega, John and
Ojha, Atul Kr. and
Kann, Katharina and
Liu, Chao-Hong",
booktitle = "Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)",
month = aug,
year = "2021",
address = "Virtual",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2021.mtsummit-loresmt.12",
pages = "124--128",
abstract = "In this paper, we describe our submissions for LoResMT Shared Task @MT Summit 2021 Conference. We built statistical translation systems in each direction for English ⇐⇒ Marathi language pair. This paper outlines initial baseline experiments with various tokenization schemes to train models. Using optimal tokenization scheme we create synthetic data and further train augmented dataset to create more statistical models. Also, we reorder English to match Marathi syntax to further train another set of baseline and data augmented models using various tokenization schemes. We report configuration of the submitted systems and results produced by them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-shrivastava-2021-a3">
<titleInfo>
<title>A3-108 Machine Translation System for LoResMT Shared Task @MT Summit 2021 Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saumitra</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our submissions for LoResMT Shared Task @MT Summit 2021 Conference. We built statistical translation systems in each direction for English ⇐⇒ Marathi language pair. This paper outlines initial baseline experiments with various tokenization schemes to train models. Using optimal tokenization scheme we create synthetic data and further train augmented dataset to create more statistical models. Also, we reorder English to match Marathi syntax to further train another set of baseline and data augmented models using various tokenization schemes. We report configuration of the submitted systems and results produced by them.</abstract>
<identifier type="citekey">yadav-shrivastava-2021-a3</identifier>
<location>
<url>https://aclanthology.org/2021.mtsummit-loresmt.12</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>124</start>
<end>128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A3-108 Machine Translation System for LoResMT Shared Task @MT Summit 2021 Conference
%A Yadav, Saumitra
%A Shrivastava, Manish
%Y Ortega, John
%Y Ojha, Atul Kr.
%Y Kann, Katharina
%Y Liu, Chao-Hong
%S Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F yadav-shrivastava-2021-a3
%X In this paper, we describe our submissions for LoResMT Shared Task @MT Summit 2021 Conference. We built statistical translation systems in each direction for English ⇐⇒ Marathi language pair. This paper outlines initial baseline experiments with various tokenization schemes to train models. Using optimal tokenization scheme we create synthetic data and further train augmented dataset to create more statistical models. Also, we reorder English to match Marathi syntax to further train another set of baseline and data augmented models using various tokenization schemes. We report configuration of the submitted systems and results produced by them.
%U https://aclanthology.org/2021.mtsummit-loresmt.12
%P 124-128
Markdown (Informal)
[A3-108 Machine Translation System for LoResMT Shared Task @MT Summit 2021 Conference](https://aclanthology.org/2021.mtsummit-loresmt.12) (Yadav & Shrivastava, LoResMT 2021)
ACL