The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing

Rik van Noord, Johan Bos


Abstract
We evaluate a semantic parser based on a character-based sequence-to-sequence model in the context of the SemEval-2017 shared task on semantic parsing for AMRs. With data augmentation, super characters, and POS-tagging we gain major improvements in performance compared to a baseline character-level model. Although we improve on previous character-based neural semantic parsing models, the overall accuracy is still lower than a state-of-the-art AMR parser. An ensemble combining our neural semantic parser with an existing, traditional parser, yields a small gain in performance.
Anthology ID:
S17-2160
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
929–933
Language:
URL:
https://aclanthology.org/S17-2160
DOI:
10.18653/v1/S17-2160
Bibkey:
Cite (ACL):
Rik van Noord and Johan Bos. 2017. The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 929–933, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing (van Noord & Bos, SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2160.pdf
Data
Bio