CLAIJul 9, 2021

Levi Graph AMR Parser using Heterogeneous Attention

arXiv:2107.04152v1712 citations
Originality Highly original
AI Analysis

This work addresses AMR parsing for natural language processing, offering a more efficient method that reduces parameter count while maintaining or improving accuracy.

The paper tackled AMR parsing by using a transformer with heterogeneous attention to predict all graph elements directly from attention matrices, achieving similar or better accuracy on AMR 2.0 and 3.0 with significantly fewer parameters than previous state-of-the-art parsers.

Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing. Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already. This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels). Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes