@inproceedings{castilho-2020-document,
title = "Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement",
author = "Castilho, Sheila",
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-nov</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>
<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-nov</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
%S Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
%D 2020
%8 nov
%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