Abstract
Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph. However, the linearisation is known to ignore the structural information. Additionally, PLMs are typically pre-trained on free text which introduces domain mismatch between pre-training and downstream G2T generation tasks. To address these shortcomings, we propose graph masking pre-training strategies that neither require supervision signals nor adjust the architecture of the underlying pre-trained encoder-decoder model. When used with a pre-trained T5, our approach achieves new state-of-the-art results on WebNLG+2020 and EventNarrative G2T generation datasets. Our method also shows to be very effective in the low-resource setting.- Anthology ID:
- 2022.emnlp-main.321
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4845–4853
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.321
- DOI:
- 10.18653/v1/2022.emnlp-main.321
- Cite (ACL):
- Jiuzhou Han and Ehsan Shareghi. 2022. Self-supervised Graph Masking Pre-training for Graph-to-Text Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4845–4853, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Self-supervised Graph Masking Pre-training for Graph-to-Text Generation (Han & Shareghi, EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.321.pdf