@inproceedings{xu-etal-2023-unsupervised,
title = "Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model",
author = "Xu, Yi and
Sheng, Shuqian and
Qi, Jiexing and
Fu, Luoyi and
Lin, Zhouhan and
Wang, Xinbing and
Zhou, Chenghu",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.281",
doi = "10.18653/v1/2023.acl-long.281",
pages = "5130--5144",
abstract = "Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for knowledge graphs. Existing unsupervised approaches become suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. However, they adopt multiple complex modules and still require entity information or relation type for training. To this end, we propose INFINITY, a simple yet effective unsupervised method with a unified pretrained language model that does not introduce external annotation tools or additional parallel information. It achieves fully unsupervised graph-text mutual conversion for the first time. Specifically, INFINITY treats both G2T and T2G as a bidirectional sequence generation task by fine-tuning only one pretrained seq2seq model. A novel back-translation-based framework is then designed to generate synthetic parallel data automatically. Besides, we investigate the impact of graph linearization and introduce the structure-aware fine-tuning strategy to alleviate possible performance deterioration via retaining structural information in graph sequences. As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks. Additionally, we also devise a new training setting called cross learning for low-resource unsupervised information extraction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-unsupervised">
<titleInfo>
<title>Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuqian</namePart>
<namePart type="family">Sheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiexing</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luoyi</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhouhan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinbing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghu</namePart>
<namePart type="family">Zhou</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for knowledge graphs. Existing unsupervised approaches become suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. However, they adopt multiple complex modules and still require entity information or relation type for training. To this end, we propose INFINITY, a simple yet effective unsupervised method with a unified pretrained language model that does not introduce external annotation tools or additional parallel information. It achieves fully unsupervised graph-text mutual conversion for the first time. Specifically, INFINITY treats both G2T and T2G as a bidirectional sequence generation task by fine-tuning only one pretrained seq2seq model. A novel back-translation-based framework is then designed to generate synthetic parallel data automatically. Besides, we investigate the impact of graph linearization and introduce the structure-aware fine-tuning strategy to alleviate possible performance deterioration via retaining structural information in graph sequences. As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks. Additionally, we also devise a new training setting called cross learning for low-resource unsupervised information extraction.</abstract>
<identifier type="citekey">xu-etal-2023-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.281</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.281</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5130</start>
<end>5144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model
%A Xu, Yi
%A Sheng, Shuqian
%A Qi, Jiexing
%A Fu, Luoyi
%A Lin, Zhouhan
%A Wang, Xinbing
%A Zhou, Chenghu
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-unsupervised
%X Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for knowledge graphs. Existing unsupervised approaches become suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. However, they adopt multiple complex modules and still require entity information or relation type for training. To this end, we propose INFINITY, a simple yet effective unsupervised method with a unified pretrained language model that does not introduce external annotation tools or additional parallel information. It achieves fully unsupervised graph-text mutual conversion for the first time. Specifically, INFINITY treats both G2T and T2G as a bidirectional sequence generation task by fine-tuning only one pretrained seq2seq model. A novel back-translation-based framework is then designed to generate synthetic parallel data automatically. Besides, we investigate the impact of graph linearization and introduce the structure-aware fine-tuning strategy to alleviate possible performance deterioration via retaining structural information in graph sequences. As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks. Additionally, we also devise a new training setting called cross learning for low-resource unsupervised information extraction.
%R 10.18653/v1/2023.acl-long.281
%U https://aclanthology.org/2023.acl-long.281
%U https://doi.org/10.18653/v1/2023.acl-long.281
%P 5130-5144
Markdown (Informal)
[Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model](https://aclanthology.org/2023.acl-long.281) (Xu et al., ACL 2023)
ACL