@inproceedings{iruskieta-etal-2019-multilingual,
title = "Multilingual segmentation based on neural networks and pre-trained word embeddings",
author = "Iruskieta, Mikel and
Bengoetxea, Kepa and
Atutxa Salazar, Aitziber and
Diaz de Ilarraza, Arantza",
editor = "Zeldes, Amir and
Das, Debopam and
Galani, Erick Maziero and
Antonio, Juliano Desiderato and
Iruskieta, Mikel",
booktitle = "Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019",
month = jun,
year = "2019",
address = "Minneapolis, MN",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2716",
doi = "10.18653/v1/W19-2716",
pages = "125--132",
abstract = "The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iruskieta-etal-2019-multilingual">
<titleInfo>
<title>Multilingual segmentation based on neural networks and pre-trained word embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Iruskieta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kepa</namePart>
<namePart type="family">Bengoetxea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitziber</namePart>
<namePart type="family">Atutxa Salazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arantza</namePart>
<namePart type="family">Diaz de Ilarraza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debopam</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erick</namePart>
<namePart type="given">Maziero</namePart>
<namePart type="family">Galani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juliano</namePart>
<namePart type="given">Desiderato</namePart>
<namePart type="family">Antonio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Iruskieta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, MN</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter.</abstract>
<identifier type="citekey">iruskieta-etal-2019-multilingual</identifier>
<identifier type="doi">10.18653/v1/W19-2716</identifier>
<location>
<url>https://aclanthology.org/W19-2716</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>125</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual segmentation based on neural networks and pre-trained word embeddings
%A Iruskieta, Mikel
%A Bengoetxea, Kepa
%A Atutxa Salazar, Aitziber
%A Diaz de Ilarraza, Arantza
%Y Zeldes, Amir
%Y Das, Debopam
%Y Galani, Erick Maziero
%Y Antonio, Juliano Desiderato
%Y Iruskieta, Mikel
%S Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, MN
%F iruskieta-etal-2019-multilingual
%X The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter.
%R 10.18653/v1/W19-2716
%U https://aclanthology.org/W19-2716
%U https://doi.org/10.18653/v1/W19-2716
%P 125-132
Markdown (Informal)
[Multilingual segmentation based on neural networks and pre-trained word embeddings](https://aclanthology.org/W19-2716) (Iruskieta et al., NAACL 2019)
ACL