AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing

Abelardo Carlos Martínez Lorenzo, Pere Lluís Huguet Cabot, Roberto Navigli


Abstract
In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. Additionally, we highlight the demanding need to compute the SMATCH score among all possible predictions. To overcome these challenges, we propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing the computational time. Our methods provide new insights for enhancing AMR parsers and metrics. Our code is available at [https://www.github.com/babelscape/AMRs-Assemble](https://www.github.com/babelscape/AMRs-Assemble).
Anthology ID:
2023.acl-short.137
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1595–1605
Language:
URL:
https://aclanthology.org/2023.acl-short.137
DOI:
10.18653/v1/2023.acl-short.137
Bibkey:
Cite (ACL):
Abelardo Carlos Martínez Lorenzo, Pere Lluís Huguet Cabot, and Roberto Navigli. 2023. AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1595–1605, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing (Martínez Lorenzo et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.137.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.137.mp4