A Partially Rule-Based Approach to AMR Generation

Emma Manning


Abstract
This paper presents a new approach to generating English text from Abstract Meaning Representation (AMR). In contrast to the neural and statistical MT approaches used in other AMR generation systems, this one is largely rule-based, supplemented only by a language model and simple statistical linearization models, allowing for more control over the output. We also address the difficulties of automatically evaluating AMR generation systems and the problems with BLEU for this task. We compare automatic metrics to human evaluations and show that while METEOR and TER arguably reflect human judgments better than BLEU, further research into suitable evaluation metrics is needed.
Anthology ID:
N19-3009
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Sudipta Kar, Farah Nadeem, Laura Burdick, Greg Durrett, Na-Rae Han
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
61–70
Language:
URL:
https://aclanthology.org/N19-3009
DOI:
10.18653/v1/N19-3009
Bibkey:
Cite (ACL):
Emma Manning. 2019. A Partially Rule-Based Approach to AMR Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 61–70, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
A Partially Rule-Based Approach to AMR Generation (Manning, NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/N19-3009.pdf