# Robust Incremental Neural Semantic Graph Parsing

arXiv: https://arxiv.org/abs/1704.07092 · HTML: https://mlsanity.com/paper/1704.07092/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2017.

## Built on by (most cited first, 13 of 13)

- [Formal Specifications from Natural Language](https://mlsanity.com/paper/2206.01962/) (2022)
- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing](https://mlsanity.com/paper/2110.15534/) (2021)
- [Comparing LLM-generated and human-authored news text using formal syntactic theory](https://mlsanity.com/paper/2506.01407/) (2025)
- [Grounded Graph Decoding Improves Compositional Generalization in Question Answering](https://mlsanity.com/paper/2111.03642/) (2021)
- [Revisiting Supertagging for Faster HPSG Pasing](https://mlsanity.com/paper/2309.07590/) (2023)
- [Weakly Supervised Reasoning by Neuro-Symbolic Approaches](https://mlsanity.com/paper/2309.13072/) (2023)
- [Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification](https://mlsanity.com/paper/2301.11459/) (2023)
- [A Transition-based Parser for Unscoped Episodic Logical Forms](https://mlsanity.com/paper/2103.08759/) (2021)
- [Spanish Resource Grammar version 2023](https://mlsanity.com/paper/2309.13318/) (2023)
- [Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing](https://mlsanity.com/paper/2110.00621/) (2021)
- [Schema-Free Dependency Parsing via Sequence Generation](https://mlsanity.com/paper/2201.12407/) (2022)
- [Exploring Graph Representations of Logical Forms for Language Modeling](https://mlsanity.com/paper/2505.14523/) (2025)

## Abstract (arXiv)

Parsing sentences to linguistically-expressive semantic representations is a key goal of Natural Language Processing. Yet statistical parsing has focused almost exclusively on bilexical dependencies or domain-specific logical forms. We propose a neural encoder-decoder transition-based parser which is the first full-coverage semantic graph parser for Minimal Recursion Semantics (MRS). The model architecture uses stack-based embedding features, predicting graphs jointly with unlexicalized predicates and their token alignments. Our parser is more accurate than attention-based baselines on MRS, and on an additional Abstract Meaning Representation (AMR) benchmark, and GPU batch processing makes it an order of magnitude faster than a high-precision grammar-based parser. Further, the 86.69% Smatch score of our MRS parser is higher than the upper-bound on AMR parsing, making MRS an attractive choice as a semantic representation.