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

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 populationlevel 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 neuralsymbolic 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. _the_q <0> _want_v_1 <2> _boy_n_1 <1> _believe_v_1 <6> _girl_n_1 <0> pron <7> pronoun_q _the_q <3> BV BV BV ARG1 ARG2 ARG1 ARG2 The <0> boy <1> wants <2> the <3> girl <4> to <5> believe <6> him <7> Abstract Concepts (grammatical function) Root Token-Node Alignments Surface Concepts (related to surface tokens) <•> (a) EDS Representation ( _want_v_1 :ARG1 ( _boy_n_1 :BV-of ( _the_q ) ) :AGR2 ( _believe_v_1 :ARG1 ( _girl_n_1 :BV-of ( _the_q ) ) :ARG2 ( pron :BV-of ( pronoun_q ) ) ) )