@inproceedings{pouran-ben-veyseh-etal-2023-generating,
title = "Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint {GPT}-2 Training",
author = "Pouran Ben Veyseh, Amir and
Dernoncourt, Franck and
Min, Bonan and
Nguyen, Thien",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.727",
doi = "10.18653/v1/2023.findings-acl.727",
pages = "11466--11478",
abstract = "Relation Extraction (RE) is the task of identifying semantic relation between real-world entities mentioned in text. Despite significant progress in RE research, a remaining challenge for RE concerns the lack of training data for data-hungry deep learning models. Cost of annotation and difficulty of the task are among hindrance to collect a large-scale RE dataset in different domains. To address this limitation, we propose a novel framework to automatically generate labeled data for RE. Our framework presents the pre-trained language model GPT-2 for data generation. In addition, to optimize the generated samples for an RE model, we introduce a meta learning approach to allow the GPT-2 model to be updated during the training process for RE. In particular, to leverage the feedback from the RE model to improve the data generation from GPT-2, we propose a novel reward function to update the GPT-2 model with REINFORCE, seeking to promote the similarity of the RE loss function{'}s gradients computed for generated data and a meta development set. We conduct extensive experiments on two benchmark datasets to produce state-of-the-art performance for RE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pouran-ben-veyseh-etal-2023-generating">
<titleInfo>
<title>Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Pouran Ben Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Relation Extraction (RE) is the task of identifying semantic relation between real-world entities mentioned in text. Despite significant progress in RE research, a remaining challenge for RE concerns the lack of training data for data-hungry deep learning models. Cost of annotation and difficulty of the task are among hindrance to collect a large-scale RE dataset in different domains. To address this limitation, we propose a novel framework to automatically generate labeled data for RE. Our framework presents the pre-trained language model GPT-2 for data generation. In addition, to optimize the generated samples for an RE model, we introduce a meta learning approach to allow the GPT-2 model to be updated during the training process for RE. In particular, to leverage the feedback from the RE model to improve the data generation from GPT-2, we propose a novel reward function to update the GPT-2 model with REINFORCE, seeking to promote the similarity of the RE loss function’s gradients computed for generated data and a meta development set. We conduct extensive experiments on two benchmark datasets to produce state-of-the-art performance for RE.</abstract>
<identifier type="citekey">pouran-ben-veyseh-etal-2023-generating</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.727</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.727</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11466</start>
<end>11478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 Training
%A Pouran Ben Veyseh, Amir
%A Dernoncourt, Franck
%A Min, Bonan
%A Nguyen, Thien
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F pouran-ben-veyseh-etal-2023-generating
%X Relation Extraction (RE) is the task of identifying semantic relation between real-world entities mentioned in text. Despite significant progress in RE research, a remaining challenge for RE concerns the lack of training data for data-hungry deep learning models. Cost of annotation and difficulty of the task are among hindrance to collect a large-scale RE dataset in different domains. To address this limitation, we propose a novel framework to automatically generate labeled data for RE. Our framework presents the pre-trained language model GPT-2 for data generation. In addition, to optimize the generated samples for an RE model, we introduce a meta learning approach to allow the GPT-2 model to be updated during the training process for RE. In particular, to leverage the feedback from the RE model to improve the data generation from GPT-2, we propose a novel reward function to update the GPT-2 model with REINFORCE, seeking to promote the similarity of the RE loss function’s gradients computed for generated data and a meta development set. We conduct extensive experiments on two benchmark datasets to produce state-of-the-art performance for RE.
%R 10.18653/v1/2023.findings-acl.727
%U https://aclanthology.org/2023.findings-acl.727
%U https://doi.org/10.18653/v1/2023.findings-acl.727
%P 11466-11478
Markdown (Informal)
[Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 Training](https://aclanthology.org/2023.findings-acl.727) (Pouran Ben Veyseh et al., Findings 2023)
ACL