Neural Text Generation from Rich Semantic Representations

Valerie Hajdik, Jan Buys, Michael Wayne Goodman, Emily M. Bender


Abstract
We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to text can achieve a BLEU score of 66.11 when trained on gold data. The performance of the model can be improved further using a high-precision, broad coverage grammar-based parser to generate a large silver training corpus, achieving a final BLEU score of 77.17 on the full test set, and 83.37 on the subset of test data most closely matching the silver data domain. Our results suggest that MRS-based representations are a good choice for applications that need both structured semantics and the ability to produce natural language text as output.
Anthology ID:
N19-1235
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2259–2266
Language:
URL:
https://www.aclweb.org/anthology/N19-1235
DOI:
10.18653/v1/N19-1235
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N19-1235.pdf