@inproceedings{desai-etal-2020-joint,
title = "Joint Learning of Syntactic Features Helps Discourse Segmentation",
author = "Desai, Takshak and
Dakle, Parag Pravin and
Moldovan, Dan",
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-1.135/",
pages = "1073--1080",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "This paper describes an accurate framework for carrying out multi-lingual discourse segmentation with BERT (Devlin et al., 2019). The model is trained to identify segments by casting the problem as a token classification problem and jointly learning syntactic features like part-of-speech tags and dependency relations. This leads to significant improvements in performance. Experiments are performed in different languages, such as English, Dutch, German, Portuguese Brazilian and Basque to highlight the cross-lingual effectiveness of the segmenter. In particular, the model achieves a state-of-the-art F-score of 96.7 for the RST-DT corpus (Carlson et al., 2003) improving on the previous best model by 7.2{\%}. Additionally, a qualitative explanation is provided for how proposed changes contribute to model performance by analyzing errors made on the test data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="desai-etal-2020-joint">
<titleInfo>
<title>Joint Learning of Syntactic Features Helps Discourse Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takshak</namePart>
<namePart type="family">Desai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parag</namePart>
<namePart type="given">Pravin</namePart>
<namePart type="family">Dakle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Moldovan</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>This paper describes an accurate framework for carrying out multi-lingual discourse segmentation with BERT (Devlin et al., 2019). The model is trained to identify segments by casting the problem as a token classification problem and jointly learning syntactic features like part-of-speech tags and dependency relations. This leads to significant improvements in performance. Experiments are performed in different languages, such as English, Dutch, German, Portuguese Brazilian and Basque to highlight the cross-lingual effectiveness of the segmenter. In particular, the model achieves a state-of-the-art F-score of 96.7 for the RST-DT corpus (Carlson et al., 2003) improving on the previous best model by 7.2%. Additionally, a qualitative explanation is provided for how proposed changes contribute to model performance by analyzing errors made on the test data.</abstract>
<identifier type="citekey">desai-etal-2020-joint</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.135/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1073</start>
<end>1080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Learning of Syntactic Features Helps Discourse Segmentation
%A Desai, Takshak
%A Dakle, Parag Pravin
%A Moldovan, Dan
%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 desai-etal-2020-joint
%X This paper describes an accurate framework for carrying out multi-lingual discourse segmentation with BERT (Devlin et al., 2019). The model is trained to identify segments by casting the problem as a token classification problem and jointly learning syntactic features like part-of-speech tags and dependency relations. This leads to significant improvements in performance. Experiments are performed in different languages, such as English, Dutch, German, Portuguese Brazilian and Basque to highlight the cross-lingual effectiveness of the segmenter. In particular, the model achieves a state-of-the-art F-score of 96.7 for the RST-DT corpus (Carlson et al., 2003) improving on the previous best model by 7.2%. Additionally, a qualitative explanation is provided for how proposed changes contribute to model performance by analyzing errors made on the test data.
%U https://aclanthology.org/2020.lrec-1.135/
%P 1073-1080
Markdown (Informal)
[Joint Learning of Syntactic Features Helps Discourse Segmentation](https://aclanthology.org/2020.lrec-1.135/) (Desai et al., LREC 2020)
ACL