@inproceedings{imanigooghari-etal-2021-graph,
title = "Graph Algorithms for Multiparallel Word Alignment",
author = {ImaniGooghari, Ayyoob and
Jalili Sabet, Masoud and
Senel, Lutfi Kerem and
Dufter, Philipp and
Yvon, Fran{\c{c}}ois and
Sch{\"u}tze, Hinrich},
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.665",
doi = "10.18653/v1/2021.emnlp-main.665",
pages = "8457--8469",
abstract = "With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts, and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario, and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit the multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements in F1 of up to 28{\%} over the baseline bilingual word aligner in different datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imanigooghari-etal-2021-graph">
<titleInfo>
<title>Graph Algorithms for Multiparallel Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayyoob</namePart>
<namePart type="family">ImaniGooghari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masoud</namePart>
<namePart type="family">Jalili Sabet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lutfi</namePart>
<namePart type="given">Kerem</namePart>
<namePart type="family">Senel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Dufter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts, and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario, and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit the multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements in F1 of up to 28% over the baseline bilingual word aligner in different datasets.</abstract>
<identifier type="citekey">imanigooghari-etal-2021-graph</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.665</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.665</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>8457</start>
<end>8469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph Algorithms for Multiparallel Word Alignment
%A ImaniGooghari, Ayyoob
%A Jalili Sabet, Masoud
%A Senel, Lutfi Kerem
%A Dufter, Philipp
%A Yvon, François
%A Schütze, Hinrich
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F imanigooghari-etal-2021-graph
%X With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts, and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario, and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit the multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements in F1 of up to 28% over the baseline bilingual word aligner in different datasets.
%R 10.18653/v1/2021.emnlp-main.665
%U https://aclanthology.org/2021.emnlp-main.665
%U https://doi.org/10.18653/v1/2021.emnlp-main.665
%P 8457-8469
Markdown (Informal)
[Graph Algorithms for Multiparallel Word Alignment](https://aclanthology.org/2021.emnlp-main.665) (ImaniGooghari et al., EMNLP 2021)
ACL
- Ayyoob ImaniGooghari, Masoud Jalili Sabet, Lutfi Kerem Senel, Philipp Dufter, François Yvon, and Hinrich Schütze. 2021. Graph Algorithms for Multiparallel Word Alignment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8457–8469, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.