@inproceedings{ortega-etal-2020-overcoming,
title = "Overcoming Resistance: The Normalization of an {A}mazonian Tribal Language",
author = "Ortega, John E and
Castro-Mamani, Richard Alexander and
Montoya Samame, Jaime Rafael",
editor = "Karakanta, Alina and
Ojha, Atul Kr. and
Liu, Chao-Hong and
Abbott, Jade and
Ortega, John and
Washington, Jonathan and
Oco, Nathaniel and
Lakew, Surafel Melaku and
Pirinen, Tommi A and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.loresmt-1.1",
doi = "10.18653/v1/2020.loresmt-1.1",
pages = "1--13",
abstract = "Languages can be considered endangered for many reasons. One of the principal reasons for endangerment is the disappearance of its speakers. Another, more identifiable reason, is the lack of written resources. We present an automated sub-segmentation system called AshMorph that deals with the morphology of an Amazonian tribal language called Ashaninka which is at risk of being endangered due to the lack of availability (or resistance) of native speakers and the absence of written resources. We show that by the use of a cross-lingual lexicon and finite state transducers we can increase accuracy by more than 30{\%} when compared to other modern sub-segmentation tools. Our results, made freely available on-line, are verified by an Ashaninka speaker and perform well in two distinct domains, everyday literary articles and the bible. This research serves as a first step in helping to preserve Ashaninka by offering a sub-segmentation process that can be used to normalize any Ashaninka text which will serve as input to a machine translation system for translation into other high-resource languages spoken by higher populated locations like Spanish and Portuguese in the case of Peru and Brazil where Ashaninka is mostly spoken.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ortega-etal-2020-overcoming">
<titleInfo>
<title>Overcoming Resistance: The Normalization of an Amazonian Tribal Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">Alexander</namePart>
<namePart type="family">Castro-Mamani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaime</namePart>
<namePart type="given">Rafael</namePart>
<namePart type="family">Montoya Samame</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</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">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surafel</namePart>
<namePart type="given">Melaku</namePart>
<namePart type="family">Lakew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Languages can be considered endangered for many reasons. One of the principal reasons for endangerment is the disappearance of its speakers. Another, more identifiable reason, is the lack of written resources. We present an automated sub-segmentation system called AshMorph that deals with the morphology of an Amazonian tribal language called Ashaninka which is at risk of being endangered due to the lack of availability (or resistance) of native speakers and the absence of written resources. We show that by the use of a cross-lingual lexicon and finite state transducers we can increase accuracy by more than 30% when compared to other modern sub-segmentation tools. Our results, made freely available on-line, are verified by an Ashaninka speaker and perform well in two distinct domains, everyday literary articles and the bible. This research serves as a first step in helping to preserve Ashaninka by offering a sub-segmentation process that can be used to normalize any Ashaninka text which will serve as input to a machine translation system for translation into other high-resource languages spoken by higher populated locations like Spanish and Portuguese in the case of Peru and Brazil where Ashaninka is mostly spoken.</abstract>
<identifier type="citekey">ortega-etal-2020-overcoming</identifier>
<identifier type="doi">10.18653/v1/2020.loresmt-1.1</identifier>
<location>
<url>https://aclanthology.org/2020.loresmt-1.1</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overcoming Resistance: The Normalization of an Amazonian Tribal Language
%A Ortega, John E.
%A Castro-Mamani, Richard Alexander
%A Montoya Samame, Jaime Rafael
%Y Karakanta, Alina
%Y Ojha, Atul Kr.
%Y Liu, Chao-Hong
%Y Abbott, Jade
%Y Ortega, John
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Lakew, Surafel Melaku
%Y Pirinen, Tommi A.
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F ortega-etal-2020-overcoming
%X Languages can be considered endangered for many reasons. One of the principal reasons for endangerment is the disappearance of its speakers. Another, more identifiable reason, is the lack of written resources. We present an automated sub-segmentation system called AshMorph that deals with the morphology of an Amazonian tribal language called Ashaninka which is at risk of being endangered due to the lack of availability (or resistance) of native speakers and the absence of written resources. We show that by the use of a cross-lingual lexicon and finite state transducers we can increase accuracy by more than 30% when compared to other modern sub-segmentation tools. Our results, made freely available on-line, are verified by an Ashaninka speaker and perform well in two distinct domains, everyday literary articles and the bible. This research serves as a first step in helping to preserve Ashaninka by offering a sub-segmentation process that can be used to normalize any Ashaninka text which will serve as input to a machine translation system for translation into other high-resource languages spoken by higher populated locations like Spanish and Portuguese in the case of Peru and Brazil where Ashaninka is mostly spoken.
%R 10.18653/v1/2020.loresmt-1.1
%U https://aclanthology.org/2020.loresmt-1.1
%U https://doi.org/10.18653/v1/2020.loresmt-1.1
%P 1-13
Markdown (Informal)
[Overcoming Resistance: The Normalization of an Amazonian Tribal Language](https://aclanthology.org/2020.loresmt-1.1) (Ortega et al., LoResMT 2020)
ACL