AMRs Assemble! 使用自回归模型进行集成学习用于 AMR 解析
AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing
AI总结：
本文针对 AMR 解析中集成策略违反结构约束的问题，提出两种基于 Transformer 的集成方法，提高鲁棒性并降低计算成本，为解析器与指标改进提供新思路。
摘要：
本文考察了当前最先进的 AMR 解析技术，该技术依赖于通过合并多个图预测的集成策略。我们的分析表明，现有模型常常违反 AMR 的结构约束。为解决此问题，我们开发了一种验证方法，并展示了集成模型如何利用 SMATCH 指标的弱点获得更高分数，但有时会导致图结构损坏。此外，我们强调在所有可能的预测中计算 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 模型的新颖集成策略，提高了对结构约束的鲁棒性，同时减少了计算时间。我们的方法为增强 AMR 解析器和指标提供了新见解。我们的代码可在 github.com/babelscape/AMRs-Assemble 获取。
英文摘要：
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}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
