Levi Graph AMR Parser using Heterogeneous Attention
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 9 Jul 2021.
Builds on
26 of 38 references.
References · 26
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
- 2018Graph-to-Sequence Learning using Gated Graph Neural Networkscited by 61
- 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
- 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
- 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
- 2020Transition-based Parsing with Stack-Transformerscited by 37
- 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
- 2016An Incremental Parser for Abstract Meaning Representationcited by 34
- 2019Broad-Coverage Semantic Parsing as Transductioncited by 32
- 2020Improving AMR Parsing with Sequence-to-Sequence Pre-trainingcited by 30
14 more
- 2019Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learningcited by 29
- 2019Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learningcited by 25
- 2019Enhancing AMR-to-Text Generation with Dual Graph Representationscited by 24
- 2019Core Semantic First: A Top-down Approach for AMR Parsingcited by 24
- 2017Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representationscited by 18
- 2018AMR Dependency Parsing with a Typed Semantic Algebracited by 17
- 2020Pushing the Limits of AMR Parsing with Self-Learningcited by 16
- 2017AMR Parsing using Stack-LSTMscited by 15
- 2019Compositional Semantic Parsing Across Graphbankscited by 15
- 2018An AMR Aligner Tuned by Transition-based Parsercited by 12
- 2016RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracycited by 11
- 2017Addressing the Data Sparsity Issue in Neural AMR Parsingcited by 11
- 2020Fast semantic parsing with well-typedness guaranteescited by 10
- 2020A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsingcited by 7
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 1.
2 papers.