@inproceedings{wiechetek-etal-2023-manual,
title = "A Manual Evaluation Method of Neural {MT} for Indigenous Languages",
author = "Wiechetek, Linda and
Pirinen, Flammie and
Kummervold, Per",
editor = "Belz, Anya and
Popovi{\'c}, Maja and
Reiter, Ehud and
Thomson, Craig and
Sedoc, Jo{\~a}o",
booktitle = "Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.humeval-1.1",
pages = "1--10",
abstract = "Indigenous language expertise is not encoded in written text in the same way as it is for languages that have a long literal tradition. In many cases it is, on the contrary, mostly conserved orally. Therefore the evaluation of neural MT systems solely based on an algorithm learning from written texts is not adequate to measure the quality of a system that is used by the language community. If extensively using tools based on a big amount of non-native language this can even contribute to language change in a way that is not desired by the language community. It can also pollute the internet with automatically created texts that outweigh native texts. We propose a manual evaluation method focusing on flow and content separately, and additionally we use existing rule-based NLP to evaluate other factors such as spelling, grammar and grammatical richness. Our main conclusion is that language expertise of a native speaker is necessary to properly evaluate a given system. We test the method by manually evaluating two neural MT tools for an indigenous low resource language. We present an experiment on two different neural translations to and from North S{\'a}mi, an indigenous language of North Europe.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wiechetek-etal-2023-manual">
<titleInfo>
<title>A Manual Evaluation Method of Neural MT for Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linda</namePart>
<namePart type="family">Wiechetek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Per</namePart>
<namePart type="family">Kummervold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Indigenous language expertise is not encoded in written text in the same way as it is for languages that have a long literal tradition. In many cases it is, on the contrary, mostly conserved orally. Therefore the evaluation of neural MT systems solely based on an algorithm learning from written texts is not adequate to measure the quality of a system that is used by the language community. If extensively using tools based on a big amount of non-native language this can even contribute to language change in a way that is not desired by the language community. It can also pollute the internet with automatically created texts that outweigh native texts. We propose a manual evaluation method focusing on flow and content separately, and additionally we use existing rule-based NLP to evaluate other factors such as spelling, grammar and grammatical richness. Our main conclusion is that language expertise of a native speaker is necessary to properly evaluate a given system. We test the method by manually evaluating two neural MT tools for an indigenous low resource language. We present an experiment on two different neural translations to and from North Sámi, an indigenous language of North Europe.</abstract>
<identifier type="citekey">wiechetek-etal-2023-manual</identifier>
<location>
<url>https://aclanthology.org/2023.humeval-1.1</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Manual Evaluation Method of Neural MT for Indigenous Languages
%A Wiechetek, Linda
%A Pirinen, Flammie
%A Kummervold, Per
%Y Belz, Anya
%Y Popović, Maja
%Y Reiter, Ehud
%Y Thomson, Craig
%Y Sedoc, João
%S Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F wiechetek-etal-2023-manual
%X Indigenous language expertise is not encoded in written text in the same way as it is for languages that have a long literal tradition. In many cases it is, on the contrary, mostly conserved orally. Therefore the evaluation of neural MT systems solely based on an algorithm learning from written texts is not adequate to measure the quality of a system that is used by the language community. If extensively using tools based on a big amount of non-native language this can even contribute to language change in a way that is not desired by the language community. It can also pollute the internet with automatically created texts that outweigh native texts. We propose a manual evaluation method focusing on flow and content separately, and additionally we use existing rule-based NLP to evaluate other factors such as spelling, grammar and grammatical richness. Our main conclusion is that language expertise of a native speaker is necessary to properly evaluate a given system. We test the method by manually evaluating two neural MT tools for an indigenous low resource language. We present an experiment on two different neural translations to and from North Sámi, an indigenous language of North Europe.
%U https://aclanthology.org/2023.humeval-1.1
%P 1-10
Markdown (Informal)
[A Manual Evaluation Method of Neural MT for Indigenous Languages](https://aclanthology.org/2023.humeval-1.1) (Wiechetek et al., HumEval-WS 2023)
ACL