# Tree Decomposition Attention for AMR-to-Text Generation

arXiv: https://arxiv.org/abs/2108.12300 · HTML: https://mlsanity.com/paper/2108.12300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Graph Transformer for Graph-to-Sequence Learning](https://mlsanity.com/paper/1911.07470/) (2019)
- [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)
- [A Graph-to-Sequence Model for AMR-to-Text Generation](https://mlsanity.com/paper/1805.02473/) (2018)
- [Modeling Graph Structure in Transformer for Better AMR-to-Text Generation](https://mlsanity.com/paper/1909.00136/) (2019)

## Abstract (arXiv)

Text generation from AMR requires mapping a semantic graph to a string that it annotates. Transformer-based graph encoders, however, poorly capture vertex dependencies that may benefit sequence prediction. To impose order on an encoder, we locally constrain vertex self-attention using a graph's tree decomposition. Instead of forming a full query-key bipartite graph, we restrict attention to vertices in parent, subtree, and same-depth bags of a vertex. This hierarchical context lends both sparsity and structure to vertex state updates. We apply dynamic programming to derive a forest of tree decompositions, choosing the most structurally similar tree to the AMR. Our system outperforms a self-attentive baseline by 1.6 BLEU and 1.8 chrF++.