Towards Collaborative Neural-Symbolic Graph Semantic Parsing via Uncertainty

Anonymous

Abstract: Recent work in task-independent graph semantic parsing has shifted from grammar-based symbolic approaches to neural models, showing strong performance on different types of meaning representations. However, it is still unclear that what are the limitations of these neural parsers, and whether these limitations can be compensated by incorporating symbolic knowledge into model inference.In this paper, we address these questions by taking English Resource Grammar (ERG) parsing as a case study. Specifically, we first develop a state-of-the-art neural ERG parser, and then conduct detail analyses of parser performance within fine-grained linguistic categories and across a wide variety of corpora. The neural parser attains superior performance on in-distribution test set, but degrades significantly on long-tail and out-of-distribution situations, while the symbolic parser performs more robustly. To address this, we further propose a simple yet principled collaborative framework for neural-symbolic semantic parsing, by designing a decision criterion for beam search that incorporates the prior knowledge from a symbolic parser and accounts for model uncertainty. Experimental results show that the proposed framework yields comprehensive improvement over neural baseline across long-tail categories and out-of-domain examples, yielding the best known result on the well-studied DeepBank benchmark.

Paper Type: long