@inproceedings{stavropoulos-etal-2023-empowering,
title = "Empowering Knowledge Discovery from Scientific Literature: A novel approach to Research Artifact Analysis",
author = "Stavropoulos, Petros and
Lyris, Ioannis and
Manola, Natalia and
Grypari, Ioanna and
Papageorgiou, Haris",
editor = "Tan, Liling and
Milajevs, Dmitrijs and
Chauhan, Geeticka and
Gwinnup, Jeremy and
Rippeth, Elijah",
booktitle = "Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlposs-1.5",
doi = "10.18653/v1/2023.nlposs-1.5",
pages = "37--53",
abstract = "Knowledge extraction from scientific literature is a major issue, crucial to promoting transparency, reproducibility, and innovation in the research community. In this work, we present a novel approach towards the identification, extraction and analysis of dataset and code/software mentions within scientific literature. We introduce a comprehensive dataset, synthetically generated by ChatGPT and meticulously curated, augmented, and expanded with real snippets of scientific text from full-text publications in Computer Science using a human-in-the-loop process. The dataset contains snippets highlighting mentions of the two research artifact (RA) types: dataset and code/software, along with insightful metadata including their Name, Version, License, URL as well as the intended Usage and Provenance. We also fine-tune a simple Large Language Model (LLM) using Low-Rank Adaptation (LoRA) to transform the Research Artifact Analysis (RAA) into an instruction-based Question Answering (QA) task. Ultimately, we report the improvements in performance on the test set of our dataset when compared to other base LLM models. Our method provides a significant step towards facilitating accurate, effective, and efficient extraction of datasets and software from scientific papers, contributing to the challenges of reproducibility and reusability in scientific research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stavropoulos-etal-2023-empowering">
<titleInfo>
<title>Empowering Knowledge Discovery from Scientific Literature: A novel approach to Research Artifact Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Petros</namePart>
<namePart type="family">Stavropoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Lyris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Manola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioanna</namePart>
<namePart type="family">Grypari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haris</namePart>
<namePart type="family">Papageorgiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeticka</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Gwinnup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elijah</namePart>
<namePart type="family">Rippeth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge extraction from scientific literature is a major issue, crucial to promoting transparency, reproducibility, and innovation in the research community. In this work, we present a novel approach towards the identification, extraction and analysis of dataset and code/software mentions within scientific literature. We introduce a comprehensive dataset, synthetically generated by ChatGPT and meticulously curated, augmented, and expanded with real snippets of scientific text from full-text publications in Computer Science using a human-in-the-loop process. The dataset contains snippets highlighting mentions of the two research artifact (RA) types: dataset and code/software, along with insightful metadata including their Name, Version, License, URL as well as the intended Usage and Provenance. We also fine-tune a simple Large Language Model (LLM) using Low-Rank Adaptation (LoRA) to transform the Research Artifact Analysis (RAA) into an instruction-based Question Answering (QA) task. Ultimately, we report the improvements in performance on the test set of our dataset when compared to other base LLM models. Our method provides a significant step towards facilitating accurate, effective, and efficient extraction of datasets and software from scientific papers, contributing to the challenges of reproducibility and reusability in scientific research.</abstract>
<identifier type="citekey">stavropoulos-etal-2023-empowering</identifier>
<identifier type="doi">10.18653/v1/2023.nlposs-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.nlposs-1.5</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>37</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Empowering Knowledge Discovery from Scientific Literature: A novel approach to Research Artifact Analysis
%A Stavropoulos, Petros
%A Lyris, Ioannis
%A Manola, Natalia
%A Grypari, Ioanna
%A Papageorgiou, Haris
%Y Tan, Liling
%Y Milajevs, Dmitrijs
%Y Chauhan, Geeticka
%Y Gwinnup, Jeremy
%Y Rippeth, Elijah
%S Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F stavropoulos-etal-2023-empowering
%X Knowledge extraction from scientific literature is a major issue, crucial to promoting transparency, reproducibility, and innovation in the research community. In this work, we present a novel approach towards the identification, extraction and analysis of dataset and code/software mentions within scientific literature. We introduce a comprehensive dataset, synthetically generated by ChatGPT and meticulously curated, augmented, and expanded with real snippets of scientific text from full-text publications in Computer Science using a human-in-the-loop process. The dataset contains snippets highlighting mentions of the two research artifact (RA) types: dataset and code/software, along with insightful metadata including their Name, Version, License, URL as well as the intended Usage and Provenance. We also fine-tune a simple Large Language Model (LLM) using Low-Rank Adaptation (LoRA) to transform the Research Artifact Analysis (RAA) into an instruction-based Question Answering (QA) task. Ultimately, we report the improvements in performance on the test set of our dataset when compared to other base LLM models. Our method provides a significant step towards facilitating accurate, effective, and efficient extraction of datasets and software from scientific papers, contributing to the challenges of reproducibility and reusability in scientific research.
%R 10.18653/v1/2023.nlposs-1.5
%U https://aclanthology.org/2023.nlposs-1.5
%U https://doi.org/10.18653/v1/2023.nlposs-1.5
%P 37-53
Markdown (Informal)
[Empowering Knowledge Discovery from Scientific Literature: A novel approach to Research Artifact Analysis](https://aclanthology.org/2023.nlposs-1.5) (Stavropoulos et al., NLPOSS-WS 2023)
ACL