Cross-lingual AMR Aligner: Paying Attention to Cross-Attention
This addresses the challenge of cross-lingual AMR alignment for NLP researchers, enabling more scalable and accurate alignment without language-specific constraints.
The paper tackles the problem of aligning Abstract Meaning Representation (AMR) graphs across different languages by leveraging Transformer-based parsers to extract alignment information from cross-attention weights, eliminating the need for English-specific rules or EM algorithms, and achieves state-of-the-art results in benchmarks.
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}.