@inproceedings{marzinotto-2020-framenet,
title = "{F}rame{N}et Annotations Alignment using Attention-based Machine Translation",
author = "Marzinotto, Gabriel",
booktitle = "Proceedings of the International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.framenet-1.6",
pages = "41--47",
abstract = "This paper presents an approach to project FrameNet annotations into other languages using attention-based neural machine translation (NMT) models. The idea is to use an NMT encoder-decoder attention matrix to propose a word-to-word correspondence between the source and the target language. We combine this word alignment along with a set of simple rules to securely project the FrameNet annotations into the target language. We successfully implemented, evaluated and analyzed this technique on the English-to-French configuration. First, we analyze the obtained FrameNet lexicon qualitatively. Then, we use existing French FrameNet corpora to assert the quality of the translation. Finally, we trained a BERT-based FrameNet parser using the projected annotations and compared it to a BERT baseline. Results show substantial improvements in the French language, giving evidence to support that our approach could help to propagate FrameNet data-set on other languages.",
language = "English",
ISBN = "979-10-95546-58-0",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marzinotto-2020-framenet">
<titleInfo>
<title>FrameNet Annotations Alignment using Attention-based Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Marzinotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-58-0</identifier>
</relatedItem>
<abstract>This paper presents an approach to project FrameNet annotations into other languages using attention-based neural machine translation (NMT) models. The idea is to use an NMT encoder-decoder attention matrix to propose a word-to-word correspondence between the source and the target language. We combine this word alignment along with a set of simple rules to securely project the FrameNet annotations into the target language. We successfully implemented, evaluated and analyzed this technique on the English-to-French configuration. First, we analyze the obtained FrameNet lexicon qualitatively. Then, we use existing French FrameNet corpora to assert the quality of the translation. Finally, we trained a BERT-based FrameNet parser using the projected annotations and compared it to a BERT baseline. Results show substantial improvements in the French language, giving evidence to support that our approach could help to propagate FrameNet data-set on other languages.</abstract>
<identifier type="citekey">marzinotto-2020-framenet</identifier>
<location>
<url>https://aclanthology.org/2020.framenet-1.6</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>41</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FrameNet Annotations Alignment using Attention-based Machine Translation
%A Marzinotto, Gabriel
%S Proceedings of the International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-58-0
%G English
%F marzinotto-2020-framenet
%X This paper presents an approach to project FrameNet annotations into other languages using attention-based neural machine translation (NMT) models. The idea is to use an NMT encoder-decoder attention matrix to propose a word-to-word correspondence between the source and the target language. We combine this word alignment along with a set of simple rules to securely project the FrameNet annotations into the target language. We successfully implemented, evaluated and analyzed this technique on the English-to-French configuration. First, we analyze the obtained FrameNet lexicon qualitatively. Then, we use existing French FrameNet corpora to assert the quality of the translation. Finally, we trained a BERT-based FrameNet parser using the projected annotations and compared it to a BERT baseline. Results show substantial improvements in the French language, giving evidence to support that our approach could help to propagate FrameNet data-set on other languages.
%U https://aclanthology.org/2020.framenet-1.6
%P 41-47
Markdown (Informal)
[FrameNet Annotations Alignment using Attention-based Machine Translation](https://aclanthology.org/2020.framenet-1.6) (Marzinotto, Framenet 2020)
ACL