论文标题
跨语言AMR对准器：注意交叉注意
Cross-lingual AMR Aligner: Paying Attention to Cross-Attention
论文作者
论文摘要
本文介绍了一个可以通过交叉语言扩展的抽象含义表示形式（AMR）图的新颖对准器，因此能够用不同语言的句子对齐单元和跨度。我们的方法利用了现代变压器的解析器，这些解析器固有地在其交叉注意权重中编码对齐信息，从而使我们能够在解析过程中提取此信息。这消除了对以前方法中使用过的英语规则或期望最大化（EM）算法的需求。此外，我们提出了一种使用对准的指导监督方法，以进一步提高对准器的性能。我们在AMR对齐的基准中实现了最先进的结果，并证明了我们对准器跨多种语言获得它们的能力。我们的代码将在\ href {https://www.github.com/babelscape/amr-alignment} {github.com/babelscape/amr-alignment}中获得。
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}.
