A Human Evaluation of AMR-to-English Generation Systems

Emma Manning, Shira Wein, Nathan Schneider


Abstract
Most current state-of-the art systems for generating English text from Abstract Meaning Representation (AMR) have been evaluated only using automated metrics, such as BLEU, which are known to be problematic for natural language generation. In this work, we present the results of a new human evaluation which collects fluency and adequacy scores, as well as categorization of error types, for several recent AMR generation systems. We discuss the relative quality of these systems and how our results compare to those of automatic metrics, finding that while the metrics are mostly successful in ranking systems overall, collecting human judgments allows for more nuanced comparisons. We also analyze common errors made by these systems.
Anthology ID:
2020.coling-main.420
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4773–4786
Language:
URL:
https://www.aclweb.org/anthology/2020.coling-main.420
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.coling-main.420.pdf