# Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification

arXiv: https://arxiv.org/abs/2301.11459 · HTML: https://mlsanity.com/paper/2301.11459/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 57 references that are in the map.
- First posted on arXiv 26 Jan 2023.

## Builds on (most cited first, 15 of 15)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [Analyzing Uncertainty in Neural Machine Translation](https://mlsanity.com/paper/1803.00047/) (2018)
- [Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://mlsanity.com/paper/1704.08381/) (2017)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [Evaluating Distributional Distortion in Neural Language Modeling](https://mlsanity.com/paper/2203.12788/) (2022)
- [Ensembling Graph Predictions for AMR Parsing](https://mlsanity.com/paper/2110.09131/) (2021)
- [Learning an Executable Neural Semantic Parser](https://mlsanity.com/paper/1711.05066/) (2017)
- [Robust Incremental Neural Semantic Graph Parsing](https://mlsanity.com/paper/1704.07092/) (2017)
- [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)
- [Graph-Based Decoding for Task Oriented Semantic Parsing](https://mlsanity.com/paper/2109.04587/) (2021)

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

- [SMATCH++: Standardized and Extended Evaluation of Semantic Graphs](https://mlsanity.com/paper/2305.06993/) (2023)
- [Spanish Resource Grammar version 2023](https://mlsanity.com/paper/2309.13318/) (2023)

## Abstract (arXiv)

Pre-trained seq2seq models excel at graph semantic parsing with rich annotated data, but generalize worse to out-of-distribution (OOD) and long-tail examples. In comparison, symbolic parsers under-perform on population-level metrics, but exhibit unique strength in OOD and tail generalization. In this work, we study compositionality-aware approach to neural-symbolic inference informed by model confidence, performing fine-grained neural-symbolic reasoning at subgraph level (i.e., nodes and edges) and precisely targeting subgraph components with high uncertainty in the neural parser. As a result, the method combines the distinct strength of the neural and symbolic approaches in capturing different aspects of the graph prediction, leading to well-rounded generalization performance both across domains and in the tail. We empirically investigate the approach in the English Resource Grammar (ERG) parsing problem on a diverse suite of standard in-domain and seven OOD corpora. Our approach leads to 35.26% and 35.60% error reduction in aggregated Smatch score over neural and symbolic approaches respectively, and 14% absolute accuracy gain in key tail linguistic categories over the neural model, outperforming prior state-of-art methods that do not account for compositionality or uncertainty.