Structural Neural Encoders for AMR-to-text Generation

Marco Damonte, Shay B. Cohen


Abstract
AMR-to-text generation is a problem recently introduced to the NLP community, in which the goal is to generate sentences from Abstract Meaning Representation (AMR) graphs. Sequence-to-sequence models can be used to this end by converting the AMR graphs to strings. Approaching the problem while working directly with graphs requires the use of graph-to-sequence models that encode the AMR graph into a vector representation. Such encoding has been shown to be beneficial in the past, and unlike sequential encoding, it allows us to explicitly capture reentrant structures in the AMR graphs. We investigate the extent to which reentrancies (nodes with multiple parents) have an impact on AMR-to-text generation by comparing graph encoders to tree encoders, where reentrancies are not preserved. We show that improvements in the treatment of reentrancies and long-range dependencies contribute to higher overall scores for graph encoders. Our best model achieves 24.40 BLEU on LDC2015E86, outperforming the state of the art by 1.1 points and 24.54 BLEU on LDC2017T10, outperforming the state of the art by 1.24 points.
Anthology ID:
N19-1366
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3649–3658
Language:
URL:
https://aclanthology.org/N19-1366
DOI:
10.18653/v1/N19-1366
Bibkey:
Cite (ACL):
Marco Damonte and Shay B. Cohen. 2019. Structural Neural Encoders for AMR-to-text Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3649–3658, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Structural Neural Encoders for AMR-to-text Generation (Damonte & Cohen, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1366.pdf
Presentation:
 N19-1366.Presentation.pdf
Code
 mdtux89/OpenNMT-py-AMR-to-text +  additional community code