# Learning compositional structures for semantic graph parsing

arXiv: https://arxiv.org/abs/2106.04398 · HTML: https://mlsanity.com/paper/2106.04398/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [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)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Span-based Semantic Parsing for Compositional Generalization](https://mlsanity.com/paper/2009.06040/) (2020)
- [Cooperative Learning of Disjoint Syntax and Semantics](https://mlsanity.com/paper/1902.09393/) (2019)
- [Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs](https://mlsanity.com/paper/1705.09189/) (2017)
- [Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT](https://mlsanity.com/paper/1908.04943/) (2019)
- [AMR Dependency Parsing with a Typed Semantic Algebra](https://mlsanity.com/paper/1805.11465/) (2018)
- [Transition-based Semantic Dependency Parsing with Pointer Networks](https://mlsanity.com/paper/2005.13344/) (2020)
- [Compositional Semantic Parsing Across Graphbanks](https://mlsanity.com/paper/1906.11746/) (2019)
- [Fast semantic parsing with well-typedness guarantees](https://mlsanity.com/paper/2009.07365/) (2020)
- [Semantic Graph Parsing with Recurrent Neural Network DAG Grammars](https://mlsanity.com/paper/1910.00051/) (2019)

## Built on by (most cited first, 3 of 3)

- [SLOG: A Structural Generalization Benchmark for Semantic Parsing](https://mlsanity.com/paper/2310.15040/) (2023)
- [Compositional Generalization Requires Compositional Parsers](https://mlsanity.com/paper/2202.11937/) (2022)
- [Scope-enhanced Compositional Semantic Parsing for DRT](https://mlsanity.com/paper/2407.01899/) (2024)

## Abstract (arXiv)

AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of the compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.