# Semantic Graph Parsing with Recurrent Neural Network DAG Grammars

arXiv: https://arxiv.org/abs/1910.00051 · HTML: https://mlsanity.com/paper/1910.00051/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation](https://mlsanity.com/paper/2306.00124/) (2023)
- [Grounded Graph Decoding Improves Compositional Generalization in Question Answering](https://mlsanity.com/paper/2111.03642/) (2021)
- [PMB5: Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks](https://mlsanity.com/paper/2404.08354/) (2024)
- [Learning compositional structures for semantic graph parsing](https://mlsanity.com/paper/2106.04398/) (2021)
- [Discourse Representation Structure Parsing for Chinese](https://mlsanity.com/paper/2306.09725/) (2023)
- [Scope-enhanced Compositional Semantic Parsing for DRT](https://mlsanity.com/paper/2407.01899/) (2024)
- [Does Character-level Information Always Improve DRS-based Semantic Parsing?](https://mlsanity.com/paper/2306.02302/) (2023)

## Abstract (arXiv)

Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the linearized graphs found in semantic parsing datasets using well-understood sequence models. The cost of this simplicity is that the predicted strings may not be well-formed graphs. We present recurrent neural network DAG grammars, a graph-aware sequence model that ensures only well-formed graphs while sidestepping many difficulties in graph prediction. We test our model on the Parallel Meaning Bank---a multilingual semantic graphbank. Our approach yields competitive results in English and establishes the first results for German, Italian and Dutch.