@inproceedings{schrader-etal-2023-mulms,
title = "{M}u{LMS}-{AZ}: An Argumentative Zoning Dataset for the Materials Science Domain",
author = {Schrader, Timo and
B{\"u}rkle, Teresa and
Henning, Sophie and
Tan, Sherry and
Finco, Matteo and
Gr{\"u}newald, Stefan and
Indrikova, Maira and
Hildebrand, Felix and
Friedrich, Annemarie},
editor = "Strube, Michael and
Braud, Chloe and
Hardmeier, Christian and
Li, Junyi Jessy and
Loaiciga, Sharid and
Zeldes, Amir",
booktitle = "Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.codi-1.1",
doi = "10.18653/v1/2023.codi-1.1",
pages = "1--15",
abstract = "Scientific publications follow conventionalized rhetorical structures. Classifying the Argumentative Zone (AZ), e.g., identifying whether a sentence states a Motivation, a Result or Background information, has been proposed to improve processing of scholarly documents. In this work, we adapt and extend this idea to the domain of materials science research. We present and release a new dataset of 50 manually annotated research articles. The dataset spans seven sub-topics and is annotated with a materials-science focused multi-label annotation scheme for AZ. We detail corpus statistics and demonstrate high inter-annotator agreement. Our computational experiments show that using domain-specific pre-trained transformer-based text encoders is key to high classification performance. We also find that AZ categories from existing datasets in other domains are transferable to varying degrees.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schrader-etal-2023-mulms">
<titleInfo>
<title>MuLMS-AZ: An Argumentative Zoning Dataset for the Materials Science Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Schrader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Bürkle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Henning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherry</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Finco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Grünewald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maira</namePart>
<namePart type="family">Indrikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Hildebrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloe</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scientific publications follow conventionalized rhetorical structures. Classifying the Argumentative Zone (AZ), e.g., identifying whether a sentence states a Motivation, a Result or Background information, has been proposed to improve processing of scholarly documents. In this work, we adapt and extend this idea to the domain of materials science research. We present and release a new dataset of 50 manually annotated research articles. The dataset spans seven sub-topics and is annotated with a materials-science focused multi-label annotation scheme for AZ. We detail corpus statistics and demonstrate high inter-annotator agreement. Our computational experiments show that using domain-specific pre-trained transformer-based text encoders is key to high classification performance. We also find that AZ categories from existing datasets in other domains are transferable to varying degrees.</abstract>
<identifier type="citekey">schrader-etal-2023-mulms</identifier>
<identifier type="doi">10.18653/v1/2023.codi-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.codi-1.1</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuLMS-AZ: An Argumentative Zoning Dataset for the Materials Science Domain
%A Schrader, Timo
%A Bürkle, Teresa
%A Henning, Sophie
%A Tan, Sherry
%A Finco, Matteo
%A Grünewald, Stefan
%A Indrikova, Maira
%A Hildebrand, Felix
%A Friedrich, Annemarie
%Y Strube, Michael
%Y Braud, Chloe
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Loaiciga, Sharid
%Y Zeldes, Amir
%S Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F schrader-etal-2023-mulms
%X Scientific publications follow conventionalized rhetorical structures. Classifying the Argumentative Zone (AZ), e.g., identifying whether a sentence states a Motivation, a Result or Background information, has been proposed to improve processing of scholarly documents. In this work, we adapt and extend this idea to the domain of materials science research. We present and release a new dataset of 50 manually annotated research articles. The dataset spans seven sub-topics and is annotated with a materials-science focused multi-label annotation scheme for AZ. We detail corpus statistics and demonstrate high inter-annotator agreement. Our computational experiments show that using domain-specific pre-trained transformer-based text encoders is key to high classification performance. We also find that AZ categories from existing datasets in other domains are transferable to varying degrees.
%R 10.18653/v1/2023.codi-1.1
%U https://aclanthology.org/2023.codi-1.1
%U https://doi.org/10.18653/v1/2023.codi-1.1
%P 1-15
Markdown (Informal)
[MuLMS-AZ: An Argumentative Zoning Dataset for the Materials Science Domain](https://aclanthology.org/2023.codi-1.1) (Schrader et al., CODI 2023)
ACL
- Timo Schrader, Teresa Bürkle, Sophie Henning, Sherry Tan, Matteo Finco, Stefan Grünewald, Maira Indrikova, Felix Hildebrand, and Annemarie Friedrich. 2023. MuLMS-AZ: An Argumentative Zoning Dataset for the Materials Science Domain. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 1–15, Toronto, Canada. Association for Computational Linguistics.