@inproceedings{castilho-2020-page,
title = "On the Same Page? Comparing Inter-Annotator Agreement in Sentence and Document Level Human Machine Translation Evaluation",
author = "Castilho, Sheila",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.137",
pages = "1150--1159",
abstract = {Document-level evaluation of machine translation has raised interest in the community especially since responses to the claims of {``}human parity{''} (Toral et al., 2018; L{\"a}ubli et al., 2018) with document-level human evaluations have been published. Yet, little is known about best practices regarding human evaluation of machine translation at the document-level. This paper presents a comparison of the differences in inter-annotator agreement between quality assessments using sentence and document-level set-ups. We report results of the agreement between professional translators for fluency and adequacy scales, error annotation, and pair-wise ranking, along with the effort needed to perform the different tasks. To best of our knowledge, this is the first study of its kind.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castilho-2020-page">
<titleInfo>
<title>On the Same Page? Comparing Inter-Annotator Agreement in Sentence and Document Level Human Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheila</namePart>
<namePart type="family">Castilho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document-level evaluation of machine translation has raised interest in the community especially since responses to the claims of “human parity” (Toral et al., 2018; Läubli et al., 2018) with document-level human evaluations have been published. Yet, little is known about best practices regarding human evaluation of machine translation at the document-level. This paper presents a comparison of the differences in inter-annotator agreement between quality assessments using sentence and document-level set-ups. We report results of the agreement between professional translators for fluency and adequacy scales, error annotation, and pair-wise ranking, along with the effort needed to perform the different tasks. To best of our knowledge, this is the first study of its kind.</abstract>
<identifier type="citekey">castilho-2020-page</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.137</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>1150</start>
<end>1159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Same Page? Comparing Inter-Annotator Agreement in Sentence and Document Level Human Machine Translation Evaluation
%A Castilho, Sheila
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F castilho-2020-page
%X Document-level evaluation of machine translation has raised interest in the community especially since responses to the claims of “human parity” (Toral et al., 2018; Läubli et al., 2018) with document-level human evaluations have been published. Yet, little is known about best practices regarding human evaluation of machine translation at the document-level. This paper presents a comparison of the differences in inter-annotator agreement between quality assessments using sentence and document-level set-ups. We report results of the agreement between professional translators for fluency and adequacy scales, error annotation, and pair-wise ranking, along with the effort needed to perform the different tasks. To best of our knowledge, this is the first study of its kind.
%U https://aclanthology.org/2020.wmt-1.137
%P 1150-1159
Markdown (Informal)
[On the Same Page? Comparing Inter-Annotator Agreement in Sentence and Document Level Human Machine Translation Evaluation](https://aclanthology.org/2020.wmt-1.137) (Castilho, WMT 2020)
ACL