@inproceedings{varachkina-pannach-2021-unified,
title = "A Unified Approach to Discourse Relation Classification in nine Languages",
author = "Varachkina, Hanna and
Pannach, Franziska",
editor = "Zeldes, Amir and
Liu, Yang Janet and
Iruskieta, Mikel and
Muller, Philippe and
Braud, Chlo{\'e} and
Badene, Sonia",
booktitle = "Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.disrpt-1.5",
doi = "10.18653/v1/2021.disrpt-1.5",
pages = "46--50",
abstract = "This paper presents efforts to solve the shared task on discourse relation classification (disrpt task 3). The intricate prediction task aims to predict a large number of classes from the Rhetorical Structure Theory (RST) framework for nine target languages. Labels include discourse relations such as background, condition, contrast and elaboration. We present an approach using euclidean distance between sentence embeddings that were extracted using multlingual sentence BERT (sBERT) and directionality as features. The data was combined into five classes which were used for initial prediction. The second classification step predicts the target classes. We observe a substantial difference in results depending on the number of occurrences of the target label in the training data. We achieve the best results on Chinese, where our system achieves 70 {\%} accuracy on 20 labels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varachkina-pannach-2021-unified">
<titleInfo>
<title>A Unified Approach to Discourse Relation Classification in nine Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Varachkina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franziska</namePart>
<namePart type="family">Pannach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)</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">Yang</namePart>
<namePart type="given">Janet</namePart>
<namePart type="family">Liu</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>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonia</namePart>
<namePart type="family">Badene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents efforts to solve the shared task on discourse relation classification (disrpt task 3). The intricate prediction task aims to predict a large number of classes from the Rhetorical Structure Theory (RST) framework for nine target languages. Labels include discourse relations such as background, condition, contrast and elaboration. We present an approach using euclidean distance between sentence embeddings that were extracted using multlingual sentence BERT (sBERT) and directionality as features. The data was combined into five classes which were used for initial prediction. The second classification step predicts the target classes. We observe a substantial difference in results depending on the number of occurrences of the target label in the training data. We achieve the best results on Chinese, where our system achieves 70 % accuracy on 20 labels.</abstract>
<identifier type="citekey">varachkina-pannach-2021-unified</identifier>
<identifier type="doi">10.18653/v1/2021.disrpt-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.disrpt-1.5</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>46</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Approach to Discourse Relation Classification in nine Languages
%A Varachkina, Hanna
%A Pannach, Franziska
%Y Zeldes, Amir
%Y Liu, Yang Janet
%Y Iruskieta, Mikel
%Y Muller, Philippe
%Y Braud, Chloé
%Y Badene, Sonia
%S Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F varachkina-pannach-2021-unified
%X This paper presents efforts to solve the shared task on discourse relation classification (disrpt task 3). The intricate prediction task aims to predict a large number of classes from the Rhetorical Structure Theory (RST) framework for nine target languages. Labels include discourse relations such as background, condition, contrast and elaboration. We present an approach using euclidean distance between sentence embeddings that were extracted using multlingual sentence BERT (sBERT) and directionality as features. The data was combined into five classes which were used for initial prediction. The second classification step predicts the target classes. We observe a substantial difference in results depending on the number of occurrences of the target label in the training data. We achieve the best results on Chinese, where our system achieves 70 % accuracy on 20 labels.
%R 10.18653/v1/2021.disrpt-1.5
%U https://aclanthology.org/2021.disrpt-1.5
%U https://doi.org/10.18653/v1/2021.disrpt-1.5
%P 46-50
Markdown (Informal)
[A Unified Approach to Discourse Relation Classification in nine Languages](https://aclanthology.org/2021.disrpt-1.5) (Varachkina & Pannach, DISRPT 2021)
ACL