Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model
Yi Xu, Shuqian Sheng, Jiexing Qi, Luoyi Fu, Zhouhan Lin, Xinbing Wang, Chenghu Zhou
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.
BibTeX
@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"
}