Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments
This work addresses a specific challenge in natural language processing for researchers and practitioners working on AMR parsing, generation, and evaluation, offering incremental improvements over existing aligners.
The paper tackles the problem of aligning Abstract Meaning Representation (AMR) graph components to English sentence spans by developing algorithms that combine unsupervised learning with heuristics, resulting in higher coverage of nodes and edges and improved accuracy compared to previous methods.
We present algorithms for aligning components of Abstract Meaning Representation (AMR) graphs to spans in English sentences. We leverage unsupervised learning in combination with heuristics, taking the best of both worlds from previous AMR aligners. Our unsupervised models, however, are more sensitive to graph substructures, without requiring a separate syntactic parse. Our approach covers a wider variety of AMR substructures than previously considered, achieves higher coverage of nodes and edges, and does so with higher accuracy. We will release our LEAMR datasets and aligner for use in research on AMR parsing, generation, and evaluation.