Semantic graph parsing with recurrent neural network DAG grammars

Federico Fancellu, Sorcha Gilroy, Adam Lopez, Mirella Lapata


Abstract
Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the *linearized* graphs found in semantic parsing datasets using well-understood sequence models. The cost of this simplicity is that the predicted strings may not be well-formed graphs. We present recurrent neural network DAG grammars, a graph-aware sequence model that generates only well-formed graphs while sidestepping many difficulties in graph prediction. We test our model on the Parallel Meaning Bank—a multilingual semantic graphbank. Our approach yields competitive results in English and establishes the first results for German, Italian and Dutch.
Anthology ID:
D19-1278
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
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2769–2778
Language:
URL:
https://aclanthology.org/D19-1278
DOI:
10.18653/v1/D19-1278
Bibkey:
Cite (ACL):
Federico Fancellu, Sorcha Gilroy, Adam Lopez, and Mirella Lapata. 2019. Semantic graph parsing with recurrent neural network DAG grammars. 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 2769–2778, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Semantic graph parsing with recurrent neural network DAG grammars (Fancellu et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1278.pdf
Attachment:
 D19-1278.Attachment.zip