@inproceedings{castilho-2021-towards,
title = "Towards Document-Level Human {MT} Evaluation: On the Issues of Annotator Agreement, Effort and Misevaluation",
author = "Castilho, Sheila",
editor = "Belz, Anya and
Agarwal, Shubham and
Graham, Yvette and
Reiter, Ehud and
Shimorina, Anastasia",
booktitle = "Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.humeval-1.4/",
pages = "34--45",
abstract = "Document-level human evaluation of machine translation (MT) has been raising interest in the community. However, little is known about the issues of using document-level methodologies to assess MT quality. In this article, we compare the inter-annotator agreement (IAA) scores, the effort to assess the quality in different document-level methodologies, and the issue of misevaluation when sentences are evaluated out of context."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castilho-2021-towards">
<titleInfo>
<title>Towards Document-Level Human MT Evaluation: On the Issues of Annotator Agreement, Effort and Misevaluation</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>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)</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">Shubham</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</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">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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 human evaluation of machine translation (MT) has been raising interest in the community. However, little is known about the issues of using document-level methodologies to assess MT quality. In this article, we compare the inter-annotator agreement (IAA) scores, the effort to assess the quality in different document-level methodologies, and the issue of misevaluation when sentences are evaluated out of context.</abstract>
<identifier type="citekey">castilho-2021-towards</identifier>
<location>
<url>https://aclanthology.org/2021.humeval-1.4/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>34</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Document-Level Human MT Evaluation: On the Issues of Annotator Agreement, Effort and Misevaluation
%A Castilho, Sheila
%Y Belz, Anya
%Y Agarwal, Shubham
%Y Graham, Yvette
%Y Reiter, Ehud
%Y Shimorina, Anastasia
%S Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F castilho-2021-towards
%X Document-level human evaluation of machine translation (MT) has been raising interest in the community. However, little is known about the issues of using document-level methodologies to assess MT quality. In this article, we compare the inter-annotator agreement (IAA) scores, the effort to assess the quality in different document-level methodologies, and the issue of misevaluation when sentences are evaluated out of context.
%U https://aclanthology.org/2021.humeval-1.4/
%P 34-45
Markdown (Informal)
[Towards Document-Level Human MT Evaluation: On the Issues of Annotator Agreement, Effort and Misevaluation](https://aclanthology.org/2021.humeval-1.4/) (Castilho, HumEval 2021)
ACL