@inproceedings{borchert-etal-2023-core,
title = "{CORE}: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation.",
author = "Borchert, Philipp and
De Weerdt, Jochen and
Coussement, Kristof and
De Caigny, Arno and
Moens, Marie-Francine",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.722",
doi = "10.18653/v1/2023.emnlp-main.722",
pages = "11792--11806",
abstract = "We introduce CORE, a dataset for few-shot relation classification (RC) focused on company relations and business entities. CORE includes 4,708 instances of 12 relation types with corresponding textual evidence extracted from company Wikipedia pages. Company names and business entities pose a challenge for few-shot RC models due to the rich and diverse information associated with them. For example, a company name may represent the legal entity, products, people, or business divisions depending on the context. Therefore, deriving the relation type between entities is highly dependent on textual context. To evaluate the performance of state-of-the-art RC models on the CORE dataset, we conduct experiments in the few-shot domain adaptation setting. Our results reveal substantial performance gaps, confirming that models trained on different domains struggle to adapt to CORE. Interestingly, we find that models trained on CORE showcase improved out-of-domain performance, which highlights the importance of high-quality data for robust domain generalization. Specifically, the information richness embedded in business entities allows models to focus on contextual nuances, reducing their reliance on superficial clues such as relation-specific verbs. In addition to the dataset, we provide relevant code snippets to facilitate reproducibility and encourage further research in the field. The CORE dataset and code are publicly available at \url{https://anonymous.4open.science/r/CORE-D377}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borchert-etal-2023-core">
<titleInfo>
<title>CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Borchert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jochen</namePart>
<namePart type="family">De Weerdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristof</namePart>
<namePart type="family">Coussement</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arno</namePart>
<namePart type="family">De Caigny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>We introduce CORE, a dataset for few-shot relation classification (RC) focused on company relations and business entities. CORE includes 4,708 instances of 12 relation types with corresponding textual evidence extracted from company Wikipedia pages. Company names and business entities pose a challenge for few-shot RC models due to the rich and diverse information associated with them. For example, a company name may represent the legal entity, products, people, or business divisions depending on the context. Therefore, deriving the relation type between entities is highly dependent on textual context. To evaluate the performance of state-of-the-art RC models on the CORE dataset, we conduct experiments in the few-shot domain adaptation setting. Our results reveal substantial performance gaps, confirming that models trained on different domains struggle to adapt to CORE. Interestingly, we find that models trained on CORE showcase improved out-of-domain performance, which highlights the importance of high-quality data for robust domain generalization. Specifically, the information richness embedded in business entities allows models to focus on contextual nuances, reducing their reliance on superficial clues such as relation-specific verbs. In addition to the dataset, we provide relevant code snippets to facilitate reproducibility and encourage further research in the field. The CORE dataset and code are publicly available at https://anonymous.4open.science/r/CORE-D377.</abstract>
<identifier type="citekey">borchert-etal-2023-core</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.722</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.722</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11792</start>
<end>11806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation.
%A Borchert, Philipp
%A De Weerdt, Jochen
%A Coussement, Kristof
%A De Caigny, Arno
%A Moens, Marie-Francine
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F borchert-etal-2023-core
%X We introduce CORE, a dataset for few-shot relation classification (RC) focused on company relations and business entities. CORE includes 4,708 instances of 12 relation types with corresponding textual evidence extracted from company Wikipedia pages. Company names and business entities pose a challenge for few-shot RC models due to the rich and diverse information associated with them. For example, a company name may represent the legal entity, products, people, or business divisions depending on the context. Therefore, deriving the relation type between entities is highly dependent on textual context. To evaluate the performance of state-of-the-art RC models on the CORE dataset, we conduct experiments in the few-shot domain adaptation setting. Our results reveal substantial performance gaps, confirming that models trained on different domains struggle to adapt to CORE. Interestingly, we find that models trained on CORE showcase improved out-of-domain performance, which highlights the importance of high-quality data for robust domain generalization. Specifically, the information richness embedded in business entities allows models to focus on contextual nuances, reducing their reliance on superficial clues such as relation-specific verbs. In addition to the dataset, we provide relevant code snippets to facilitate reproducibility and encourage further research in the field. The CORE dataset and code are publicly available at https://anonymous.4open.science/r/CORE-D377.
%R 10.18653/v1/2023.emnlp-main.722
%U https://aclanthology.org/2023.emnlp-main.722
%U https://doi.org/10.18653/v1/2023.emnlp-main.722
%P 11792-11806
Markdown (Informal)
[CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation.](https://aclanthology.org/2023.emnlp-main.722) (Borchert et al., EMNLP 2023)
ACL