@inproceedings{imani-etal-2022-graph,
title = "Graph Neural Networks for Multiparallel Word Alignment",
author = {Imani, Ayyoob and
Senel, L{\"u}tfi Kerem and
Jalili Sabet, Masoud and
Yvon, Fran{\c{c}}ois and
Schuetze, Hinrich},
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.108",
doi = "10.18653/v1/2022.findings-acl.108",
pages = "1384--1396",
abstract = "After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection algorithms can provide valuable information for multiparallel word alignment. Our method outperforms previous work on three word alignment datasets and on a downstream task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imani-etal-2022-graph">
<titleInfo>
<title>Graph Neural Networks for Multiparallel Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayyoob</namePart>
<namePart type="family">Imani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lütfi</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">Masoud</namePart>
<namePart type="family">Jalili Sabet</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">Schuetze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection algorithms can provide valuable information for multiparallel word alignment. Our method outperforms previous work on three word alignment datasets and on a downstream task.</abstract>
<identifier type="citekey">imani-etal-2022-graph</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.108</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.108</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1384</start>
<end>1396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph Neural Networks for Multiparallel Word Alignment
%A Imani, Ayyoob
%A Senel, Lütfi Kerem
%A Jalili Sabet, Masoud
%A Yvon, François
%A Schuetze, Hinrich
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F imani-etal-2022-graph
%X After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection algorithms can provide valuable information for multiparallel word alignment. Our method outperforms previous work on three word alignment datasets and on a downstream task.
%R 10.18653/v1/2022.findings-acl.108
%U https://aclanthology.org/2022.findings-acl.108
%U https://doi.org/10.18653/v1/2022.findings-acl.108
%P 1384-1396
Markdown (Informal)
[Graph Neural Networks for Multiparallel Word Alignment](https://aclanthology.org/2022.findings-acl.108) (Imani et al., Findings 2022)
ACL
- Ayyoob Imani, Lütfi Kerem Senel, Masoud Jalili Sabet, François Yvon, and Hinrich Schuetze. 2022. Graph Neural Networks for Multiparallel Word Alignment. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1384–1396, Dublin, Ireland. Association for Computational Linguistics.