@inproceedings{yousef-etal-2022-automatic,
title = "An automatic model and Gold Standard for translation alignment of {A}ncient {G}reek",
author = "Yousef, Tariq and
Palladino, Chiara and
Shamsian, Farnoosh and
d{'}Orange Ferreira, Anise and
Ferreira dos Reis, Michel",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.634",
pages = "5894--5905",
abstract = "This paper illustrates a workflow for developing and evaluating automatic translation alignment models for Ancient Greek. We designed an annotation Style Guide and a gold standard for the alignment of Ancient Greek-English and Ancient Greek-Portuguese, measured inter-annotator agreement and used the resulting dataset to evaluate the performance of various translation alignment models. We proposed a fine-tuning strategy that employs unsupervised training with mono- and bilingual texts and supervised training using manually aligned sentences. The results indicate that the fine-tuned model based on XLM-Roberta is superior in performance, and it achieved good results on language pairs that were not part of the training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yousef-etal-2022-automatic">
<titleInfo>
<title>An automatic model and Gold Standard for translation alignment of Ancient Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tariq</namePart>
<namePart type="family">Yousef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Palladino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farnoosh</namePart>
<namePart type="family">Shamsian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anise</namePart>
<namePart type="family">d’Orange Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Ferreira dos Reis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper illustrates a workflow for developing and evaluating automatic translation alignment models for Ancient Greek. We designed an annotation Style Guide and a gold standard for the alignment of Ancient Greek-English and Ancient Greek-Portuguese, measured inter-annotator agreement and used the resulting dataset to evaluate the performance of various translation alignment models. We proposed a fine-tuning strategy that employs unsupervised training with mono- and bilingual texts and supervised training using manually aligned sentences. The results indicate that the fine-tuned model based on XLM-Roberta is superior in performance, and it achieved good results on language pairs that were not part of the training data.</abstract>
<identifier type="citekey">yousef-etal-2022-automatic</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.634</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5894</start>
<end>5905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An automatic model and Gold Standard for translation alignment of Ancient Greek
%A Yousef, Tariq
%A Palladino, Chiara
%A Shamsian, Farnoosh
%A d’Orange Ferreira, Anise
%A Ferreira dos Reis, Michel
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F yousef-etal-2022-automatic
%X This paper illustrates a workflow for developing and evaluating automatic translation alignment models for Ancient Greek. We designed an annotation Style Guide and a gold standard for the alignment of Ancient Greek-English and Ancient Greek-Portuguese, measured inter-annotator agreement and used the resulting dataset to evaluate the performance of various translation alignment models. We proposed a fine-tuning strategy that employs unsupervised training with mono- and bilingual texts and supervised training using manually aligned sentences. The results indicate that the fine-tuned model based on XLM-Roberta is superior in performance, and it achieved good results on language pairs that were not part of the training data.
%U https://aclanthology.org/2022.lrec-1.634
%P 5894-5905
Markdown (Informal)
[An automatic model and Gold Standard for translation alignment of Ancient Greek](https://aclanthology.org/2022.lrec-1.634) (Yousef et al., LREC 2022)
ACL