@inproceedings{bechara-etal-2024-creating,
title = "Creating and Evaluating a Multilingual Corpus of {UN} General Assembly Debates",
author = "Bechara, Hannah and
Manohara, Krishnamoorthy and
Jankin, Slava",
editor = "Scarton, Carolina and
Prescott, Charlotte and
Bayliss, Chris and
Oakley, Chris and
Wright, Joanna and
Wrigley, Stuart and
Song, Xingyi and
Gow-Smith, Edward and
Bawden, Rachel and
S{\'a}nchez-Cartagena, V{\'\i}ctor M and
Cadwell, Patrick and
Lapshinova-Koltunski, Ekaterina and
Cabarr{\~a}o, Vera and
Chatzitheodorou, Konstantinos and
Nurminen, Mary and
Kanojia, Diptesh and
Moniz, Helena",
booktitle = "Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)",
month = jun,
year = "2024",
address = "Sheffield, UK",
publisher = "European Association for Machine Translation (EAMT)",
url = "https://aclanthology.org/2024.eamt-1.52",
pages = "623--627",
abstract = "This paper presents a multilingual aligned corpus of political debates from the United Nations (UN) General Assembly sessions between 1978 and 2021, which covers five of the six official UN languages: Arabic, Chinese, English, French, Russian, and Spanish. We explain the preprocessing steps we applied to the corpus. We align the sentences by using word vectors to numerically represent the meaning of each sentence and then calculating the Euclidean distance between them. To validate our alignment methods, we conducted an evaluation study with crowd-sourced human annotators using Scale AI, an online platform for data labelling. The final dataset consists of around 300,000 aligned sentences for En-Es, En-Fr, En-Zh and En-Ru. It is publicly available for download.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bechara-etal-2024-creating">
<titleInfo>
<title>Creating and Evaluating a Multilingual Corpus of UN General Assembly Debates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Bechara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishnamoorthy</namePart>
<namePart type="family">Manohara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slava</namePart>
<namePart type="family">Jankin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="family">Prescott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Bayliss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Oakley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stuart</namePart>
<namePart type="family">Wrigley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Gow-Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Cadwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Cabarrão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Chatzitheodorou</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">Diptesh</namePart>
<namePart type="family">Kanojia</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>
<originInfo>
<publisher>European Association for Machine Translation (EAMT)</publisher>
<place>
<placeTerm type="text">Sheffield, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a multilingual aligned corpus of political debates from the United Nations (UN) General Assembly sessions between 1978 and 2021, which covers five of the six official UN languages: Arabic, Chinese, English, French, Russian, and Spanish. We explain the preprocessing steps we applied to the corpus. We align the sentences by using word vectors to numerically represent the meaning of each sentence and then calculating the Euclidean distance between them. To validate our alignment methods, we conducted an evaluation study with crowd-sourced human annotators using Scale AI, an online platform for data labelling. The final dataset consists of around 300,000 aligned sentences for En-Es, En-Fr, En-Zh and En-Ru. It is publicly available for download.</abstract>
<identifier type="citekey">bechara-etal-2024-creating</identifier>
<location>
<url>https://aclanthology.org/2024.eamt-1.52</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>623</start>
<end>627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating and Evaluating a Multilingual Corpus of UN General Assembly Debates
%A Bechara, Hannah
%A Manohara, Krishnamoorthy
%A Jankin, Slava
%Y Scarton, Carolina
%Y Prescott, Charlotte
%Y Bayliss, Chris
%Y Oakley, Chris
%Y Wright, Joanna
%Y Wrigley, Stuart
%Y Song, Xingyi
%Y Gow-Smith, Edward
%Y Bawden, Rachel
%Y Sánchez-Cartagena, Víctor M.
%Y Cadwell, Patrick
%Y Lapshinova-Koltunski, Ekaterina
%Y Cabarrão, Vera
%Y Chatzitheodorou, Konstantinos
%Y Nurminen, Mary
%Y Kanojia, Diptesh
%Y Moniz, Helena
%S Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2024
%8 June
%I European Association for Machine Translation (EAMT)
%C Sheffield, UK
%F bechara-etal-2024-creating
%X This paper presents a multilingual aligned corpus of political debates from the United Nations (UN) General Assembly sessions between 1978 and 2021, which covers five of the six official UN languages: Arabic, Chinese, English, French, Russian, and Spanish. We explain the preprocessing steps we applied to the corpus. We align the sentences by using word vectors to numerically represent the meaning of each sentence and then calculating the Euclidean distance between them. To validate our alignment methods, we conducted an evaluation study with crowd-sourced human annotators using Scale AI, an online platform for data labelling. The final dataset consists of around 300,000 aligned sentences for En-Es, En-Fr, En-Zh and En-Ru. It is publicly available for download.
%U https://aclanthology.org/2024.eamt-1.52
%P 623-627
Markdown (Informal)
[Creating and Evaluating a Multilingual Corpus of UN General Assembly Debates](https://aclanthology.org/2024.eamt-1.52) (Bechara et al., EAMT 2024)
ACL