Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification
Lin, Zi, Liu, Jeremiah, Shang, Jingbo
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-26-2023
- Country:
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- United States
- Pennsylvania > Philadelphia County
- Philadelphia (0.14)
- Illinois > Cook County
- Chicago (0.04)
- Colorado > Denver County
- Denver (0.04)
- California > San Diego County
- San Diego (0.04)
- Pennsylvania > Philadelphia County
- Canada > British Columbia
- Europe
- Germany (0.04)
- Latvia > Riga Municipality
- Riga (0.04)
- France > Grand Est
- Meurthe-et-Moselle > Nancy (0.04)
- Iceland > Capital Region
- Reykjavik (0.04)
- Spain > Valencian Community
- Valencia Province > Valencia (0.04)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Italy > Liguria
- Genoa (0.04)
- Greece > Attica
- Athens (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Asia
- Genre:
- Research Report (0.50)
- Technology: