@inproceedings{kiepura-etal-2024-scipara,
title = "{S}ci{P}ara: A New Dataset for Investigating Paragraph Discourse Structure in Scientific Papers",
author = "Kiepura, Anna and
Gao, Yingqiang and
Lam, Jessica and
Gu, Nianlong and
Hahnloser, Richard H.r.",
editor = "Strube, Michael and
Braud, Chloe and
Hardmeier, Christian and
Li, Junyi Jessy and
Loaiciga, Sharid and
Zeldes, Amir and
Li, Chuyuan",
booktitle = "Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024)",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.codi-1.2",
pages = "12--26",
abstract = "Good scientific writing makes use of specific sentence and paragraph structures, providing a rich platform for discourse analysis and developing tools to enhance text readability. In this vein, we introduce SciPara, a novel dataset consisting of 981 scientific paragraphs annotated by experts in terms of sentence discourse types and topic information. On this dataset, we explored two tasks: 1) discourse category classification, which is to predict the discourse category of a sentence by using its paragraph and surrounding paragraphs as context, and 2) discourse sentence generation, which is to generate a sentence of a certain discourse category by using various contexts as input. We found that Pre-trained Language Models (PLMs) can accurately identify Topic Sentences in SciPara, but have difficulty distinguishing Concluding, Transition, and Supporting Sentences. The quality of the sentences generated by all investigated PLMs improved with amount of context, regardless of discourse category. However, not all contexts were equally influential. Contrary to common assumptions about well-crafted scientific paragraphs, our analysis revealed that paradoxically, paragraphs with complete discourse structures were less readable.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kiepura-etal-2024-scipara">
<titleInfo>
<title>SciPara: A New Dataset for Investigating Paragraph Discourse Structure in Scientific Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kiepura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingqiang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianlong</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">H.r.</namePart>
<namePart type="family">Hahnloser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024)</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>
<name type="personal">
<namePart type="given">Chuyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Good scientific writing makes use of specific sentence and paragraph structures, providing a rich platform for discourse analysis and developing tools to enhance text readability. In this vein, we introduce SciPara, a novel dataset consisting of 981 scientific paragraphs annotated by experts in terms of sentence discourse types and topic information. On this dataset, we explored two tasks: 1) discourse category classification, which is to predict the discourse category of a sentence by using its paragraph and surrounding paragraphs as context, and 2) discourse sentence generation, which is to generate a sentence of a certain discourse category by using various contexts as input. We found that Pre-trained Language Models (PLMs) can accurately identify Topic Sentences in SciPara, but have difficulty distinguishing Concluding, Transition, and Supporting Sentences. The quality of the sentences generated by all investigated PLMs improved with amount of context, regardless of discourse category. However, not all contexts were equally influential. Contrary to common assumptions about well-crafted scientific paragraphs, our analysis revealed that paradoxically, paragraphs with complete discourse structures were less readable.</abstract>
<identifier type="citekey">kiepura-etal-2024-scipara</identifier>
<location>
<url>https://aclanthology.org/2024.codi-1.2</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>12</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SciPara: A New Dataset for Investigating Paragraph Discourse Structure in Scientific Papers
%A Kiepura, Anna
%A Gao, Yingqiang
%A Lam, Jessica
%A Gu, Nianlong
%A Hahnloser, Richard H.r.
%Y Strube, Michael
%Y Braud, Chloe
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Loaiciga, Sharid
%Y Zeldes, Amir
%Y Li, Chuyuan
%S Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F kiepura-etal-2024-scipara
%X Good scientific writing makes use of specific sentence and paragraph structures, providing a rich platform for discourse analysis and developing tools to enhance text readability. In this vein, we introduce SciPara, a novel dataset consisting of 981 scientific paragraphs annotated by experts in terms of sentence discourse types and topic information. On this dataset, we explored two tasks: 1) discourse category classification, which is to predict the discourse category of a sentence by using its paragraph and surrounding paragraphs as context, and 2) discourse sentence generation, which is to generate a sentence of a certain discourse category by using various contexts as input. We found that Pre-trained Language Models (PLMs) can accurately identify Topic Sentences in SciPara, but have difficulty distinguishing Concluding, Transition, and Supporting Sentences. The quality of the sentences generated by all investigated PLMs improved with amount of context, regardless of discourse category. However, not all contexts were equally influential. Contrary to common assumptions about well-crafted scientific paragraphs, our analysis revealed that paradoxically, paragraphs with complete discourse structures were less readable.
%U https://aclanthology.org/2024.codi-1.2
%P 12-26
Markdown (Informal)
[SciPara: A New Dataset for Investigating Paragraph Discourse Structure in Scientific Papers](https://aclanthology.org/2024.codi-1.2) (Kiepura et al., CODI-WS 2024)
ACL