Abstract
Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges. To address this difficulty, we propose a novel graph-to-sequence model that encodes different but complementary perspectives of the structural information contained in the AMR graph. The model learns parallel top-down and bottom-up representations of nodes capturing contrasting views of the graph. We also investigate the use of different node message passing strategies, employing different state-of-the-art graph encoders to compute node representations based on incoming and outgoing perspectives. In our experiments, we demonstrate that the dual graph representation leads to improvements in AMR-to-text generation, achieving state-of-the-art results on two AMR datasets- Anthology ID:
- D19-1314
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3183–3194
- Language:
- URL:
- https://aclanthology.org/D19-1314
- DOI:
- 10.18653/v1/D19-1314
- Cite (ACL):
- Leonardo F. R. Ribeiro, Claire Gardent, and Iryna Gurevych. 2019. Enhancing AMR-to-Text Generation with Dual Graph Representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3183–3194, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Enhancing AMR-to-Text Generation with Dual Graph Representations (Ribeiro et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/D19-1314.pdf
- Code
- UKPLab/emnlp2019-dualgraph
- Data
- LDC2017T10