Abstract
Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However, PLMs are typically pre-trained on textual data, thus are sub-optimal for modeling structural knowledge. To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs. In particular, we introduce two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-training. We further design a unified framework to bridge the gap between pre-training and fine-tuning tasks. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pre-training on semantic graphs.- Anthology ID:
- 2022.acl-long.415
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6001–6015
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.415
- DOI:
- 10.18653/v1/2022.acl-long.415
- Cite (ACL):
- Xuefeng Bai, Yulong Chen, and Yue Zhang. 2022. Graph Pre-training for AMR Parsing and Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6001–6015, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Graph Pre-training for AMR Parsing and Generation (Bai et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.acl-long.415.pdf
- Code
- muyeby/amrbart + additional community code
- Data
- Bio, LDC2017T10, LDC2020T02, New3, The Little Prince