@inproceedings{zugarini-etal-2023-buster,
title = "{BUSTER}: a {``}{BUS}iness Transaction Entity Recognition{''} dataset",
author = "Zugarini, Andrea and
Zamai, Andrew and
Ernandes, Marco and
Rigutini, Leonardo",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.57",
doi = "10.18653/v1/2023.emnlp-industry.57",
pages = "605--611",
abstract = "Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reasons resides in the displacement between popular benchmarks and actual data. Lack of supervision, unbalanced classes, noisy data and long documents often affect real problems in vertical domains such as finance, law and health. To support industry-oriented research, we present BUSTER, a BUSiness Transaction Entity Recognition dataset. The dataset consists of 3779 manually annotated documents on financial transactions. We establish several baselines exploiting both general-purpose and domain-specific language models. The best performing model is also used to automatically annotate 6196 documents, which we release as an additional silver corpus to BUSTER.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zugarini-etal-2023-buster">
<titleInfo>
<title>BUSTER: a “BUSiness Transaction Entity Recognition” dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Zugarini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Zamai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Ernandes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Rigutini</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 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</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>Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reasons resides in the displacement between popular benchmarks and actual data. Lack of supervision, unbalanced classes, noisy data and long documents often affect real problems in vertical domains such as finance, law and health. To support industry-oriented research, we present BUSTER, a BUSiness Transaction Entity Recognition dataset. The dataset consists of 3779 manually annotated documents on financial transactions. We establish several baselines exploiting both general-purpose and domain-specific language models. The best performing model is also used to automatically annotate 6196 documents, which we release as an additional silver corpus to BUSTER.</abstract>
<identifier type="citekey">zugarini-etal-2023-buster</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.57</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.57</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>605</start>
<end>611</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BUSTER: a “BUSiness Transaction Entity Recognition” dataset
%A Zugarini, Andrea
%A Zamai, Andrew
%A Ernandes, Marco
%A Rigutini, Leonardo
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zugarini-etal-2023-buster
%X Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reasons resides in the displacement between popular benchmarks and actual data. Lack of supervision, unbalanced classes, noisy data and long documents often affect real problems in vertical domains such as finance, law and health. To support industry-oriented research, we present BUSTER, a BUSiness Transaction Entity Recognition dataset. The dataset consists of 3779 manually annotated documents on financial transactions. We establish several baselines exploiting both general-purpose and domain-specific language models. The best performing model is also used to automatically annotate 6196 documents, which we release as an additional silver corpus to BUSTER.
%R 10.18653/v1/2023.emnlp-industry.57
%U https://aclanthology.org/2023.emnlp-industry.57
%U https://doi.org/10.18653/v1/2023.emnlp-industry.57
%P 605-611
Markdown (Informal)
[BUSTER: a “BUSiness Transaction Entity Recognition” dataset](https://aclanthology.org/2023.emnlp-industry.57) (Zugarini et al., EMNLP 2023)
ACL
- Andrea Zugarini, Andrew Zamai, Marco Ernandes, and Leonardo Rigutini. 2023. BUSTER: a “BUSiness Transaction Entity Recognition” dataset. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 605–611, Singapore. Association for Computational Linguistics.