Syntactic realization with data-driven neural tree grammars

Brian McMahan, Matthew Stone


Abstract
A key component in surface realization in natural language generation is to choose concrete syntactic relationships to express a target meaning. We develop a new method for syntactic choice based on learning a stochastic tree grammar in a neural architecture. This framework can exploit state-of-the-art methods for modeling word sequences and generalizing across vocabulary. We also induce embeddings to generalize over elementary tree structures and exploit a tree recurrence over the input structure to model long-distance influences between NLG choices. We evaluate the models on the task of linearizing unannotated dependency trees, documenting the contribution of our modeling techniques to improvements in both accuracy and run time.
Anthology ID:
C16-1022
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
224–235
Language:
URL:
https://aclanthology.org/C16-1022
DOI:
Bibkey:
Cite (ACL):
Brian McMahan and Matthew Stone. 2016. Syntactic realization with data-driven neural tree grammars. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 224–235, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Syntactic realization with data-driven neural tree grammars (McMahan & Stone, COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1022.pdf
Code
 braingineer/neural_tree_grammar