AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing
This work addresses incremental improvements in AMR parsing for natural language processing researchers by enhancing ensemble methods and metrics.
The paper tackles the problem of AMR parsing ensembles violating structural constraints and exploiting metric weaknesses, proposing two novel Transformer-based ensemble strategies that improve robustness and reduce computational time.
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 \href{https://www.github.com/babelscape/AMRs-Assemble}{github.com/babelscape/AMRs-Assemble}.