# Levi Graph AMR Parser using Heterogeneous Attention

arXiv: https://arxiv.org/abs/2107.04152 · HTML: https://mlsanity.com/paper/2107.04152/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 9 Jul 2021.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Graph-to-Sequence Learning using Gated Graph Neural Networks](https://mlsanity.com/paper/1806.09835/) (2018)
- [Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://mlsanity.com/paper/1704.08381/) (2017)
- [AMR Parsing as Sequence-to-Graph Transduction](https://mlsanity.com/paper/1905.08704/) (2019)
- [AMR Parsing via Graph-Sequence Iterative Inference](https://mlsanity.com/paper/2004.05572/) (2020)
- [Transition-based Parsing with Stack-Transformers](https://mlsanity.com/paper/2010.10669/) (2020)
- [AMR Parsing as Graph Prediction with Latent Alignment](https://mlsanity.com/paper/1805.05286/) (2018)
- [An Incremental Parser for Abstract Meaning Representation](https://mlsanity.com/paper/1608.06111/) (2016)
- [Broad-Coverage Semantic Parsing as Transduction](https://mlsanity.com/paper/1909.02607/) (2019)
- [Improving AMR Parsing with Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2010.01771/) (2020)
- [Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning](https://mlsanity.com/paper/1908.05957/) (2019)
- [Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning](https://mlsanity.com/paper/1905.13370/) (2019)
- [Enhancing AMR-to-Text Generation with Dual Graph Representations](https://mlsanity.com/paper/1909.00352/) (2019)
- [Core Semantic First: A Top-down Approach for AMR Parsing](https://mlsanity.com/paper/1909.04303/) (2019)
- [Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations](https://mlsanity.com/paper/1705.09980/) (2017)
- [AMR Dependency Parsing with a Typed Semantic Algebra](https://mlsanity.com/paper/1805.11465/) (2018)
- [Pushing the Limits of AMR Parsing with Self-Learning](https://mlsanity.com/paper/2010.10673/) (2020)
- [AMR Parsing using Stack-LSTMs](https://mlsanity.com/paper/1707.07755/) (2017)
- [Compositional Semantic Parsing Across Graphbanks](https://mlsanity.com/paper/1906.11746/) (2019)
- [An AMR Aligner Tuned by Transition-based Parser](https://mlsanity.com/paper/1810.03541/) (2018)
- [RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy](https://mlsanity.com/paper/1604.01278/) (2016)
- [Addressing the Data Sparsity Issue in Neural AMR Parsing](https://mlsanity.com/paper/1702.05053/) (2017)
- [Fast semantic parsing with well-typedness guarantees](https://mlsanity.com/paper/2009.07365/) (2020)
- [A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing](https://mlsanity.com/paper/2010.12676/) (2020)

## Built on by (most cited first, 2 of 2)

- [ELIT: Emory Language and Information Toolkit](https://mlsanity.com/paper/2109.03903/) (2021)
- [Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing](https://mlsanity.com/paper/2302.02275/) (2023)

## 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.