@inproceedings{ramirez-orta-etal-2025-rouge,
title = "{ROUGE}-{S}ci{QFS}: A {ROUGE}-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization",
author = "Ramirez-Orta, Juan and
Maguitman, Ana and
Soto, Axel J. and
Milios, Evangelos",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.149/",
pages = "2187--2197",
abstract = "So far, the task of Scientific Query-Focused Summarization (Sci-QFS) has lagged in development when compared to other areas of Scientific Natural Language Processing because of the lack of data. In this work, we propose a methodology to take advantage of existing collections of academic papers to obtain large-scale datasets for this task automatically. After applying it to the papers from our reading group, we introduce a novel dataset for Sci-QFS composed of 8,695 examples, each one with a query, the sentences of the full text from a paper and the relevance labels for each. After testing several classical and state-of-the-art embedding models on this data, we found that the task of Sci-QFS is far from being solved, although it is relatively straightforward for humans. Surprisingly, we found that classical methods outperformed modern pre-trained Deep Language Models (sometimes by a large margin), showing the need for large datasets to better fine-tune the latter. We share our experiments, data and models at https://github.com/jarobyte91/rouge{\_}sciqfs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramirez-orta-etal-2025-rouge">
<titleInfo>
<title>ROUGE-SciQFS: A ROUGE-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Ramirez-Orta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Maguitman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Soto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evangelos</namePart>
<namePart type="family">Milios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>So far, the task of Scientific Query-Focused Summarization (Sci-QFS) has lagged in development when compared to other areas of Scientific Natural Language Processing because of the lack of data. In this work, we propose a methodology to take advantage of existing collections of academic papers to obtain large-scale datasets for this task automatically. After applying it to the papers from our reading group, we introduce a novel dataset for Sci-QFS composed of 8,695 examples, each one with a query, the sentences of the full text from a paper and the relevance labels for each. After testing several classical and state-of-the-art embedding models on this data, we found that the task of Sci-QFS is far from being solved, although it is relatively straightforward for humans. Surprisingly, we found that classical methods outperformed modern pre-trained Deep Language Models (sometimes by a large margin), showing the need for large datasets to better fine-tune the latter. We share our experiments, data and models at https://github.com/jarobyte91/rouge_sciqfs.</abstract>
<identifier type="citekey">ramirez-orta-etal-2025-rouge</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.149/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>2187</start>
<end>2197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ROUGE-SciQFS: A ROUGE-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization
%A Ramirez-Orta, Juan
%A Maguitman, Ana
%A Soto, Axel J.
%A Milios, Evangelos
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ramirez-orta-etal-2025-rouge
%X So far, the task of Scientific Query-Focused Summarization (Sci-QFS) has lagged in development when compared to other areas of Scientific Natural Language Processing because of the lack of data. In this work, we propose a methodology to take advantage of existing collections of academic papers to obtain large-scale datasets for this task automatically. After applying it to the papers from our reading group, we introduce a novel dataset for Sci-QFS composed of 8,695 examples, each one with a query, the sentences of the full text from a paper and the relevance labels for each. After testing several classical and state-of-the-art embedding models on this data, we found that the task of Sci-QFS is far from being solved, although it is relatively straightforward for humans. Surprisingly, we found that classical methods outperformed modern pre-trained Deep Language Models (sometimes by a large margin), showing the need for large datasets to better fine-tune the latter. We share our experiments, data and models at https://github.com/jarobyte91/rouge_sciqfs.
%U https://aclanthology.org/2025.coling-main.149/
%P 2187-2197
Markdown (Informal)
[ROUGE-SciQFS: A ROUGE-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization](https://aclanthology.org/2025.coling-main.149/) (Ramirez-Orta et al., COLING 2025)
ACL