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.
2023, Findings of the Association for Computational Linguistics: ACL 2023, Pages 1726-1742
Cross-lingual AMR Aligner: Paying Attention to Cross-Attention (04b Atto di convegno in volume)
Martinez Lorenzo Abelardo Carlos, Huguet Cabot Pere Lluís, Navigli Roberto