How much of UCCA can be predicted from AMR?

Siyana Pavlova, Maxime Amblard, Bruno Guillaume


Abstract
In this paper, we consider two of the currently popular semantic frameworks: Abstract Meaning Representation (AMR) - a more abstract framework, and Universal Conceptual Cognitive Annotation (UCCA) - an anchored framework. We use a corpus-based approach to build two graph rewriting systems, a deterministic and a non-deterministic one, from the former to the latter framework. We present their evaluation and a number of ambiguities that we discovered while building our rules. Finally, we provide a discussion and some future work directions in relation to comparing semantic frameworks of different flavors.
Anthology ID:
2022.isa-1.15
Volume:
Proceedings of the 18th Joint ACL - ISO Workshop on Interoperable Semantic Annotation within LREC2022
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
ISA
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
110–117
Language:
URL:
https://aclanthology.org/2022.isa-1.15
DOI:
Bibkey:
Cite (ACL):
Siyana Pavlova, Maxime Amblard, and Bruno Guillaume. 2022. How much of UCCA can be predicted from AMR?. In Proceedings of the 18th Joint ACL - ISO Workshop on Interoperable Semantic Annotation within LREC2022, pages 110–117, Marseille, France. European Language Resources Association.
Cite (Informal):
How much of UCCA can be predicted from AMR? (Pavlova et al., ISA 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.isa-1.15.pdf
Data
AMR Bank