A Graph-to-Sequence Model for AMR-to-Text Generation

Linfeng Song, Yue Zhang, Zhiguo Wang, Daniel Gildea


Abstract
The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. Although being able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus facing challenges with large-graphs, which result in long sequences. We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics. On a standard benchmark, our model shows superior results to existing methods in the literature.
Anthology ID:
P18-1150
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1616–1626
Language:
URL:
https://aclanthology.org/P18-1150
DOI:
10.18653/v1/P18-1150
Bibkey:
Cite (ACL):
Linfeng Song, Yue Zhang, Zhiguo Wang, and Daniel Gildea. 2018. A Graph-to-Sequence Model for AMR-to-Text Generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1616–1626, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
A Graph-to-Sequence Model for AMR-to-Text Generation (Song et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1150.pdf
Poster:
 P18-1150.Poster.pdf
Code
 freesunshine0316/neural-graph-to-seq-mp