@inproceedings{plum-etal-2024-guided-distant,
title = "Guided Distant Supervision for Multilingual Relation Extraction Data: Adapting to a New Language",
author = "Plum, Alistair and
Ranasinghe, Tharindu and
Purschke, Christoph",
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.703",
pages = "7982--7992",
abstract = "Relation extraction is essential for extracting and understanding biographical information in the context of digital humanities and related subjects. There is a growing interest in the community to build datasets capable of training machine learning models to extract relationships. However, annotating such datasets can be expensive and time-consuming, in addition to being limited to English. This paper applies guided distant supervision to create a large biographical relationship extraction dataset for German. Our dataset, composed of more than 80,000 instances for nine relationship types, is the largest biographical German relationship extraction dataset. We also create a manually annotated dataset with 2000 instances to evaluate the models and release it together with the dataset compiled using guided distant supervision. We train several state-of-the-art machine learning models on the automatically created dataset and release them as well. Furthermore, we experiment with multilingual and cross-lingual zero-shot experiments that could benefit many low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plum-etal-2024-guided-distant">
<titleInfo>
<title>Guided Distant Supervision for Multilingual Relation Extraction Data: Adapting to a New Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Purschke</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 essential for extracting and understanding biographical information in the context of digital humanities and related subjects. There is a growing interest in the community to build datasets capable of training machine learning models to extract relationships. However, annotating such datasets can be expensive and time-consuming, in addition to being limited to English. This paper applies guided distant supervision to create a large biographical relationship extraction dataset for German. Our dataset, composed of more than 80,000 instances for nine relationship types, is the largest biographical German relationship extraction dataset. We also create a manually annotated dataset with 2000 instances to evaluate the models and release it together with the dataset compiled using guided distant supervision. We train several state-of-the-art machine learning models on the automatically created dataset and release them as well. Furthermore, we experiment with multilingual and cross-lingual zero-shot experiments that could benefit many low-resource languages.</abstract>
<identifier type="citekey">plum-etal-2024-guided-distant</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.703</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7982</start>
<end>7992</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Guided Distant Supervision for Multilingual Relation Extraction Data: Adapting to a New Language
%A Plum, Alistair
%A Ranasinghe, Tharindu
%A Purschke, Christoph
%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 plum-etal-2024-guided-distant
%X Relation extraction is essential for extracting and understanding biographical information in the context of digital humanities and related subjects. There is a growing interest in the community to build datasets capable of training machine learning models to extract relationships. However, annotating such datasets can be expensive and time-consuming, in addition to being limited to English. This paper applies guided distant supervision to create a large biographical relationship extraction dataset for German. Our dataset, composed of more than 80,000 instances for nine relationship types, is the largest biographical German relationship extraction dataset. We also create a manually annotated dataset with 2000 instances to evaluate the models and release it together with the dataset compiled using guided distant supervision. We train several state-of-the-art machine learning models on the automatically created dataset and release them as well. Furthermore, we experiment with multilingual and cross-lingual zero-shot experiments that could benefit many low-resource languages.
%U https://aclanthology.org/2024.lrec-main.703
%P 7982-7992
Markdown (Informal)
[Guided Distant Supervision for Multilingual Relation Extraction Data: Adapting to a New Language](https://aclanthology.org/2024.lrec-main.703) (Plum et al., LREC-COLING 2024)
ACL