@inproceedings{sluyter-gathje-etal-2020-shallow,
title = "Shallow Discourse Parsing for Under-Resourced Languages: Combining Machine Translation and Annotation Projection",
author = {Sluyter-G{\"a}thje, Henny and
Bourgonje, Peter and
Stede, Manfred},
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.131/",
pages = "1044--1050",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Shallow Discourse Parsing (SDP), the identification of coherence relations between text spans, relies on large amounts of training data, which so far exists only for English - any other language is in this respect an under-resourced one. For those languages where machine translation from English is available with reasonable quality, MT in conjunction with annotation projection can be an option for producing an SDP resource. In our study, we translate the English Penn Discourse TreeBank into German and experiment with various methods of annotation projection to arrive at the German counterpart of the PDTB. We describe the key characteristics of the corpus as well as some typical sources of errors encountered during its creation. Then we evaluate the GermanPDTB by training components for selected sub-tasks of discourse parsing on this silver data and compare performance to the same components when trained on the gold, original PDTB corpus."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sluyter-gathje-etal-2020-shallow">
<titleInfo>
<title>Shallow Discourse Parsing for Under-Resourced Languages: Combining Machine Translation and Annotation Projection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henny</namePart>
<namePart type="family">Sluyter-Gäthje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Bourgonje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Shallow Discourse Parsing (SDP), the identification of coherence relations between text spans, relies on large amounts of training data, which so far exists only for English - any other language is in this respect an under-resourced one. For those languages where machine translation from English is available with reasonable quality, MT in conjunction with annotation projection can be an option for producing an SDP resource. In our study, we translate the English Penn Discourse TreeBank into German and experiment with various methods of annotation projection to arrive at the German counterpart of the PDTB. We describe the key characteristics of the corpus as well as some typical sources of errors encountered during its creation. Then we evaluate the GermanPDTB by training components for selected sub-tasks of discourse parsing on this silver data and compare performance to the same components when trained on the gold, original PDTB corpus.</abstract>
<identifier type="citekey">sluyter-gathje-etal-2020-shallow</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.131/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1044</start>
<end>1050</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shallow Discourse Parsing for Under-Resourced Languages: Combining Machine Translation and Annotation Projection
%A Sluyter-Gäthje, Henny
%A Bourgonje, Peter
%A Stede, Manfred
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F sluyter-gathje-etal-2020-shallow
%X Shallow Discourse Parsing (SDP), the identification of coherence relations between text spans, relies on large amounts of training data, which so far exists only for English - any other language is in this respect an under-resourced one. For those languages where machine translation from English is available with reasonable quality, MT in conjunction with annotation projection can be an option for producing an SDP resource. In our study, we translate the English Penn Discourse TreeBank into German and experiment with various methods of annotation projection to arrive at the German counterpart of the PDTB. We describe the key characteristics of the corpus as well as some typical sources of errors encountered during its creation. Then we evaluate the GermanPDTB by training components for selected sub-tasks of discourse parsing on this silver data and compare performance to the same components when trained on the gold, original PDTB corpus.
%U https://aclanthology.org/2020.lrec-1.131/
%P 1044-1050
Markdown (Informal)
[Shallow Discourse Parsing for Under-Resourced Languages: Combining Machine Translation and Annotation Projection](https://aclanthology.org/2020.lrec-1.131/) (Sluyter-Gäthje et al., LREC 2020)
ACL