AMR Parsing as Sequence-to-Graph Transduction
ACL (1), pp. 80-94, 2019.
We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is aligner-free, and it can be effectively trained with limited amounts of labeled AMR data. Our experimental res...More
PPT (Upload PPT)