@inproceedings{kong-etal-2024-mixred,
title = "{M}ix{RED}: A Mix-lingual Relation Extraction Dataset",
author = "Kong, Lingxing and
Chu, Yougang and
Ma, Zheng and
Zhang, Jianbing and
He, Liang and
Chen, Jiajun",
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.993",
pages = "11361--11370",
abstract = "Relation extraction is a critical task in the field of natural language processing with numerous real-world applications. Existing research primarily focuses on monolingual relation extraction or cross-lingual enhancement for relation extraction. Yet, there remains a significant gap in understanding relation extraction in the mix-lingual (or code-switching) scenario, where individuals intermix contents from different languages within sentences, generating mix-lingual content. Due to the lack of a dedicated dataset, the effectiveness of existing relation extraction models in such a scenario is largely unexplored. To address this issue, we introduce a novel task of considering relation extraction in the mix-lingual scenario called MixRE and constructing the human-annotated dataset MixRED to support this task. In addition to constructing the MixRED dataset, we evaluate both state-of-the-art supervised models and large language models (LLMs) on MixRED, revealing their respective advantages and limitations in the mix-lingual scenario. Furthermore, we delve into factors influencing model performance within the MixRE task and uncover promising directions for enhancing the performance of both supervised models and LLMs in this novel task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kong-etal-2024-mixred">
<titleInfo>
<title>MixRED: A Mix-lingual Relation Extraction Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingxing</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yougang</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianbing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Chen</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>Relation extraction is a critical task in the field of natural language processing with numerous real-world applications. Existing research primarily focuses on monolingual relation extraction or cross-lingual enhancement for relation extraction. Yet, there remains a significant gap in understanding relation extraction in the mix-lingual (or code-switching) scenario, where individuals intermix contents from different languages within sentences, generating mix-lingual content. Due to the lack of a dedicated dataset, the effectiveness of existing relation extraction models in such a scenario is largely unexplored. To address this issue, we introduce a novel task of considering relation extraction in the mix-lingual scenario called MixRE and constructing the human-annotated dataset MixRED to support this task. In addition to constructing the MixRED dataset, we evaluate both state-of-the-art supervised models and large language models (LLMs) on MixRED, revealing their respective advantages and limitations in the mix-lingual scenario. Furthermore, we delve into factors influencing model performance within the MixRE task and uncover promising directions for enhancing the performance of both supervised models and LLMs in this novel task.</abstract>
<identifier type="citekey">kong-etal-2024-mixred</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.993</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11361</start>
<end>11370</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MixRED: A Mix-lingual Relation Extraction Dataset
%A Kong, Lingxing
%A Chu, Yougang
%A Ma, Zheng
%A Zhang, Jianbing
%A He, Liang
%A Chen, Jiajun
%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 kong-etal-2024-mixred
%X Relation extraction is a critical task in the field of natural language processing with numerous real-world applications. Existing research primarily focuses on monolingual relation extraction or cross-lingual enhancement for relation extraction. Yet, there remains a significant gap in understanding relation extraction in the mix-lingual (or code-switching) scenario, where individuals intermix contents from different languages within sentences, generating mix-lingual content. Due to the lack of a dedicated dataset, the effectiveness of existing relation extraction models in such a scenario is largely unexplored. To address this issue, we introduce a novel task of considering relation extraction in the mix-lingual scenario called MixRE and constructing the human-annotated dataset MixRED to support this task. In addition to constructing the MixRED dataset, we evaluate both state-of-the-art supervised models and large language models (LLMs) on MixRED, revealing their respective advantages and limitations in the mix-lingual scenario. Furthermore, we delve into factors influencing model performance within the MixRE task and uncover promising directions for enhancing the performance of both supervised models and LLMs in this novel task.
%U https://aclanthology.org/2024.lrec-main.993
%P 11361-11370
Markdown (Informal)
[MixRED: A Mix-lingual Relation Extraction Dataset](https://aclanthology.org/2024.lrec-main.993) (Kong et al., LREC-COLING 2024)
ACL
- Lingxing Kong, Yougang Chu, Zheng Ma, Jianbing Zhang, Liang He, and Jiajun Chen. 2024. MixRED: A Mix-lingual Relation Extraction Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11361–11370, Torino, Italia. ELRA and ICCL.