Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks

William Foland, James H. Martin


Abstract
We present a system which parses sentences into Abstract Meaning Representations, improving state-of-the-art results for this task by more than 5%. AMR graphs represent semantic content using linguistic properties such as semantic roles, coreference, negation, and more. The AMR parser does not rely on a syntactic pre-parse, or heavily engineered features, and uses five recurrent neural networks as the key architectural components for inferring AMR graphs.
Anthology ID:
P17-1043
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
463–472
Language:
URL:
https://aclanthology.org/P17-1043
DOI:
10.18653/v1/P17-1043
Bibkey:
Cite (ACL):
William Foland and James H. Martin. 2017. Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 463–472, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks (Foland & Martin, ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1043.pdf
Video:
 https://aclanthology.org/P17-1043.mp4
Code
 BillFoland/daisyluAMR