@inproceedings{rezapour-etal-2024-two,
title = "Two-Stage Graph-Augmented Summarization of Scientific Documents",
author = "Rezapour, Rezvaneh and
Ge, Yubin and
Han, Kanyao and
Jeong, Ray and
Diesner, Jana",
editor = "Peled-Cohen, Lotem and
Calderon, Nitay and
Lissak, Shir and
Reichart, Roi",
booktitle = "Proceedings of the 1st Workshop on NLP for Science (NLP4Science)",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4science-1.5",
doi = "10.18653/v1/2024.nlp4science-1.5",
pages = "36--46",
abstract = "Automatic text summarization helps to digest the vast and ever-growing amount of scientific publications. While transformer-based solutions like BERT and SciBERT have advanced scientific summarization, lengthy documents pose a challenge due to the token limits of these models. To address this issue, we introduce and evaluate a two-stage model that combines an extract-then-compress framework. Our model incorporates a {``}graph-augmented extraction module{''} to select order-based salient sentences and an {``}abstractive compression module{''} to generate concise summaries. Additionally, we introduce the *BioConSumm* dataset, which focuses on biodiversity conservation, to support underrepresented domains and explore domain-specific summarization strategies. Out of the tested models, our model achieves the highest ROUGE-2 and ROUGE-L scores on our newly created dataset (*BioConSumm*) and on the *SUMPUBMED* dataset, which serves as a benchmark in the field of biomedicine.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rezapour-etal-2024-two">
<titleInfo>
<title>Two-Stage Graph-Augmented Summarization of Scientific Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rezvaneh</namePart>
<namePart type="family">Rezapour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubin</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanyao</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ray</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Diesner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on NLP for Science (NLP4Science)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lotem</namePart>
<namePart type="family">Peled-Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitay</namePart>
<namePart type="family">Calderon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shir</namePart>
<namePart type="family">Lissak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic text summarization helps to digest the vast and ever-growing amount of scientific publications. While transformer-based solutions like BERT and SciBERT have advanced scientific summarization, lengthy documents pose a challenge due to the token limits of these models. To address this issue, we introduce and evaluate a two-stage model that combines an extract-then-compress framework. Our model incorporates a “graph-augmented extraction module” to select order-based salient sentences and an “abstractive compression module” to generate concise summaries. Additionally, we introduce the *BioConSumm* dataset, which focuses on biodiversity conservation, to support underrepresented domains and explore domain-specific summarization strategies. Out of the tested models, our model achieves the highest ROUGE-2 and ROUGE-L scores on our newly created dataset (*BioConSumm*) and on the *SUMPUBMED* dataset, which serves as a benchmark in the field of biomedicine.</abstract>
<identifier type="citekey">rezapour-etal-2024-two</identifier>
<identifier type="doi">10.18653/v1/2024.nlp4science-1.5</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4science-1.5</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>36</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Two-Stage Graph-Augmented Summarization of Scientific Documents
%A Rezapour, Rezvaneh
%A Ge, Yubin
%A Han, Kanyao
%A Jeong, Ray
%A Diesner, Jana
%Y Peled-Cohen, Lotem
%Y Calderon, Nitay
%Y Lissak, Shir
%Y Reichart, Roi
%S Proceedings of the 1st Workshop on NLP for Science (NLP4Science)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F rezapour-etal-2024-two
%X Automatic text summarization helps to digest the vast and ever-growing amount of scientific publications. While transformer-based solutions like BERT and SciBERT have advanced scientific summarization, lengthy documents pose a challenge due to the token limits of these models. To address this issue, we introduce and evaluate a two-stage model that combines an extract-then-compress framework. Our model incorporates a “graph-augmented extraction module” to select order-based salient sentences and an “abstractive compression module” to generate concise summaries. Additionally, we introduce the *BioConSumm* dataset, which focuses on biodiversity conservation, to support underrepresented domains and explore domain-specific summarization strategies. Out of the tested models, our model achieves the highest ROUGE-2 and ROUGE-L scores on our newly created dataset (*BioConSumm*) and on the *SUMPUBMED* dataset, which serves as a benchmark in the field of biomedicine.
%R 10.18653/v1/2024.nlp4science-1.5
%U https://aclanthology.org/2024.nlp4science-1.5
%U https://doi.org/10.18653/v1/2024.nlp4science-1.5
%P 36-46
Markdown (Informal)
[Two-Stage Graph-Augmented Summarization of Scientific Documents](https://aclanthology.org/2024.nlp4science-1.5) (Rezapour et al., NLP4Science 2024)
ACL