Synthetic Dataset of Citation Strings in 12 Styles

This dataset was produced in the aim of testing different tools for citation string parsing, as part of the experiment reported in the paper: Iana Atanassova and Marc Bertin, 2024. "Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers", Bibliometric-enhanced Information Retrieval workshop (BIR), collocated with ECIR 2024, Glasgow, Scotland. Data The data that is provided here is organised as follows: the file citation-strings.zip contains raw citation strings that were generated for each of the 12 citation styles in txt format the file parsers-output.csv contains the output that was produced from the parsers: ChatGPT, Llama, and Neural ParsCit To cite this work To use this dataset and/or the results produced in the experiment, please cite the following article: @inproceedings{atanassova2024citparse, title = {{Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers}}, author = {Iana Atanassova and Marc Bertin}, year = {2024}, booktitle = {{International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2024) co-located with the 46\textsuperscript{st} European Conference on Information Retrieval (ECIR 2024)}}, address = {Glasgow, Scotland}} Authors information Iana Atanassova, ORCID https://orcid.org/0000-0003-3571-4006 URL https://iana-atanassova.github.io/ Marc Bertin, ORCID https://orcid.org/0000-0003-1803-6952 URL https://elico-recherche.msh-lse.fr/membres/marc-bertin Related github repository https://github.com/iana-atanassova/citation-parsers-bir2024.git本数据集专为测试各类引文字符串解析工具而构建，相关实验成果已发表于以下论文： Iana Atanassova 与 Marc Bertin，2024年。《引文解析领域的边界突破：生成式大语言模型（Generative Large Language Models）与传统开箱即用引文解析器的对比研究》，收录于与第46届欧洲信息检索大会（ECIR 2024）联合举办的文献计量增强信息检索研讨会（BIR），举办地为苏格兰格拉斯哥。 ## 数据说明 本次提供的数据组织形式如下： 1. `citation-strings.zip`：包含针对12种引文格式生成的原始引文字符串，均以TXT格式存储。 2. `parsers-output.csv`：包含各解析工具的输出结果，涉及ChatGPT、Llama以及神经ParsCit（Neural ParsCit）。 ## 引用本数据集及实验成果 若需使用本数据集及/或本实验生成的结果，请引用以下论文： bibtex @inproceedings{atanassova2024citparse, title = {{Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers}}, author = {Iana Atanassova and Marc Bertin}, year = {2024}, booktitle = {{International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2024) co-located with the 46 extsuperscript{th} European Conference on Information Retrieval (ECIR 2024)}}, address = {Glasgow, Scotland} } ## 作者信息 Iana Atanassova，ORCID：https://orcid.org/0000-0003-3571-4006，个人主页：https://iana-atanassova.github.io/ Marc Bertin，ORCID：https://orcid.org/0000-0003-1803-6952，个人主页：https://elico-recherche.msh-lse.fr/membres/marc-bertin ## 相关GitHub仓库 https://github.com/iana-atanassova/citation-parsers-bir2024.git