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}.

翻译：本文考察了当前AMR解析领域的最先进技术，该技术通过合并多个图预测结果来依赖集成策略。我们的分析揭示，现有模型往往违反AMR结构约束。为解决这一问题，我们开发了一种验证方法，并展示了集成模型如何利用SMATCH评估指标的弱点获得更高分数，但有时会导致图结构损坏。此外，我们强调了在所有可能预测结果中计算SMATCH分数的迫切需求。为克服这些挑战，我们提出了两种基于Transformer模型的新型集成策略，在提升对结构约束鲁棒性的同时，显著降低了计算时间。我们的方法为改进AMR解析器与评估指标提供了新思路。代码已开源在 \href{https://www.github.com/babelscape/AMRs-Assemble}{github.com/babelscape/AMRs-Assemble}。