跨语言AMR对齐器：关注交叉注意力
Cross-lingual AMR Aligner: Paying Attention to Cross-Attention
AI总结：
本文提出一种跨语言AMR对齐器，利用Transformer解析器的交叉注意力提取对齐信息，无需英语规则或EM算法，并通过引导监督方法提升性能，在AMR对齐基准上取得多语言最先进结果。
摘要：
本文介绍了一种新颖的用于抽象意义表示（AMR）图的对齐器，它能够跨语言扩展，从而能够对齐不同语言句子中的单元和跨度。我们的方法利用了现代的基于Transformer的解析器，这些解析器在其交叉注意力权重中固有地编码了对齐信息，使我们能够在解析过程中提取这些信息。这消除了对英语特定规则或先前方法中使用的期望最大化（EM）算法的需求。此外，我们提出了一种使用对齐的引导监督方法，以进一步增强我们对齐器的性能。我们在AMR对齐基准上取得了最先进的结果，并展示了我们的对齐器在多种语言上获得这些结果的能力。我们的代码将在github.com/Babelscape/AMR-alignment上提供。
英文摘要：
This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern Transformer-based parsers, which inherently encode alignment information in their cross-attention weights, allowing us to extract this information during parsing. This eliminates the need for English-specific rules or the Expectation Maximization (EM) algorithm that have been used in previous approaches. In addition, we propose a guided supervised method using alignment to further enhance the performance of our aligner. We achieve state-of-the-art results in the benchmarks for AMR alignment and demonstrate our aligner's ability to obtain them across multiple languages. Our code will be available at \href{https://www.github.com/Babelscape/AMR-alignment}{github.com/Babelscape/AMR-alignment}.
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。
