@inproceedings{castilho-2020-document,
title = "Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement",
author = "Castilho, Sheila",
editor = "Martins, Andr{\'e} and
Moniz, Helena and
Fumega, Sara and
Martins, Bruno and
Batista, Fernando and
Coheur, Luisa and
Parra, Carla and
Trancoso, Isabel and
Turchi, Marco and
Bisazza, Arianna and
Moorkens, Joss and
Guerberof, Ana and
Nurminen, Mary and
Marg, Lena and
Forcada, Mikel L.",
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.49",
pages = "455--456",
abstract = "Document-level (doc-level) human eval-uation of machine translation (MT) has raised interest in the community after a fewattempts have disproved claims of {``}human parity{''} (Toral et al., 2018; Laubli et al.,2018). However, little is known about bestpractices regarding doc-level human evalu-ation. The goal of this project is to identifywhich methodologies better cope with i)the current state-of-the-art (SOTA) humanmetrics, ii) a possible complexity when as-signing a single score to a text consisted of{`}good{'} and {`}bad{'} sentences, iii) a possibletiredness bias in doc-level set-ups, and iv)the difference in inter-annotator agreement(IAA) between sentence and doc-level set-ups.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castilho-2020-document">
<titleInfo>
<title>Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement</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>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Fumega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Batista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Parra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joss</namePart>
<namePart type="family">Moorkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Guerberof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Marg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Lisboa, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document-level (doc-level) human eval-uation of machine translation (MT) has raised interest in the community after a fewattempts have disproved claims of “human parity” (Toral et al., 2018; Laubli et al.,2018). However, little is known about bestpractices regarding doc-level human evalu-ation. The goal of this project is to identifywhich methodologies better cope with i)the current state-of-the-art (SOTA) humanmetrics, ii) a possible complexity when as-signing a single score to a text consisted of‘good’ and ‘bad’ sentences, iii) a possibletiredness bias in doc-level set-ups, and iv)the difference in inter-annotator agreement(IAA) between sentence and doc-level set-ups.</abstract>
<identifier type="citekey">castilho-2020-document</identifier>
<location>
<url>https://aclanthology.org/2020.eamt-1.49</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>455</start>
<end>456</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement
%A Castilho, Sheila
%Y Martins, André
%Y Moniz, Helena
%Y Fumega, Sara
%Y Martins, Bruno
%Y Batista, Fernando
%Y Coheur, Luisa
%Y Parra, Carla
%Y Trancoso, Isabel
%Y Turchi, Marco
%Y Bisazza, Arianna
%Y Moorkens, Joss
%Y Guerberof, Ana
%Y Nurminen, Mary
%Y Marg, Lena
%Y Forcada, Mikel L.
%S Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
%D 2020
%8 November
%I European Association for Machine Translation
%C Lisboa, Portugal
%F castilho-2020-document
%X Document-level (doc-level) human eval-uation of machine translation (MT) has raised interest in the community after a fewattempts have disproved claims of “human parity” (Toral et al., 2018; Laubli et al.,2018). However, little is known about bestpractices regarding doc-level human evalu-ation. The goal of this project is to identifywhich methodologies better cope with i)the current state-of-the-art (SOTA) humanmetrics, ii) a possible complexity when as-signing a single score to a text consisted of‘good’ and ‘bad’ sentences, iii) a possibletiredness bias in doc-level set-ups, and iv)the difference in inter-annotator agreement(IAA) between sentence and doc-level set-ups.
%U https://aclanthology.org/2020.eamt-1.49
%P 455-456
Markdown (Informal)
[Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement](https://aclanthology.org/2020.eamt-1.49) (Castilho, EAMT 2020)
ACL