@inproceedings{hamotskyi-etal-2024-fincorpus,
title = "{F}in{C}orpus-{DE}10k: A Corpus for the {G}erman Financial Domain",
author = {Hamotskyi, Serhii and
Kozaeva, Nata and
H{\"a}nig, Christian},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.639",
pages = "7277--7285",
abstract = "We introduce a predominantly German corpus comprising 12.5k PDF documents sourced from the financial domain. The corresponding extracted textual data encompasses more than 165 million tokens derived predominantly from German, and to a lesser extent, bilingual documents. We provide detailed information about the document types included in the corpus, such as final terms, base prospectuses, annual reports, information materials, law documents, international financial reporting standards, and monthly reports from the Bundesbank, accompanied by comprehensive statistical analysis. To our knowledge, it is the first non-email German financial corpus available, and we hope it will fill this gap and foster further research in the financial domain both in the German language and in multilingual contexts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamotskyi-etal-2024-fincorpus">
<titleInfo>
<title>FinCorpus-DE10k: A Corpus for the German Financial Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Serhii</namePart>
<namePart type="family">Hamotskyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nata</namePart>
<namePart type="family">Kozaeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hänig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a predominantly German corpus comprising 12.5k PDF documents sourced from the financial domain. The corresponding extracted textual data encompasses more than 165 million tokens derived predominantly from German, and to a lesser extent, bilingual documents. We provide detailed information about the document types included in the corpus, such as final terms, base prospectuses, annual reports, information materials, law documents, international financial reporting standards, and monthly reports from the Bundesbank, accompanied by comprehensive statistical analysis. To our knowledge, it is the first non-email German financial corpus available, and we hope it will fill this gap and foster further research in the financial domain both in the German language and in multilingual contexts.</abstract>
<identifier type="citekey">hamotskyi-etal-2024-fincorpus</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.639</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7277</start>
<end>7285</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FinCorpus-DE10k: A Corpus for the German Financial Domain
%A Hamotskyi, Serhii
%A Kozaeva, Nata
%A Hänig, Christian
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F hamotskyi-etal-2024-fincorpus
%X We introduce a predominantly German corpus comprising 12.5k PDF documents sourced from the financial domain. The corresponding extracted textual data encompasses more than 165 million tokens derived predominantly from German, and to a lesser extent, bilingual documents. We provide detailed information about the document types included in the corpus, such as final terms, base prospectuses, annual reports, information materials, law documents, international financial reporting standards, and monthly reports from the Bundesbank, accompanied by comprehensive statistical analysis. To our knowledge, it is the first non-email German financial corpus available, and we hope it will fill this gap and foster further research in the financial domain both in the German language and in multilingual contexts.
%U https://aclanthology.org/2024.lrec-main.639
%P 7277-7285
Markdown (Informal)
[FinCorpus-DE10k: A Corpus for the German Financial Domain](https://aclanthology.org/2024.lrec-main.639) (Hamotskyi et al., LREC-COLING 2024)
ACL
- Serhii Hamotskyi, Nata Kozaeva, and Christian Hänig. 2024. FinCorpus-DE10k: A Corpus for the German Financial Domain. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7277–7285, Torino, Italia. ELRA and ICCL.