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

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

DOI：
10.48550/arxiv.2301.11459
复制
发表时间：
2023-01
期刊：
ArXiv
影响因子：
--
通讯作者：
Zi Lin;J. Liu;Jingbo Shang
Zi Lin;J. Liu;Jingbo Shang
中科院分区：
其他
文献类型：
--
作者：
Zi Lin;J. Liu;Jingbo Shang

文献摘要

相似文献

预训练的seq2seq模型在具有丰富注释数据的图语义解析方面表现出色，但对分布外（OOD）和长尾示例的泛化能力较差。相比之下，符号解析器在人口级指标上表现不佳，但在OOD和尾部泛化方面表现出独特的优势。在这项工作中，我们研究了由模型置信度提供信息的组合感知神经符号推理方法，在子图级别（即，节点和边），并在神经解析器中精确地瞄准具有高不确定性的子图分量。因此，该方法结合了神经和符号方法在捕获图预测的不同方面的独特优势，从而在跨域和尾部都具有全面的泛化性能。我们实证研究的方法在英语资源语法（ERG）的分析问题上的一套不同的标准领域和七个面向对象的语料库。我们的方法分别比神经和符号方法减少了35.26%和35.60%的聚合SMATCH得分错误，并且比神经模型在关键尾部语言类别中获得了14%的绝对准确度，优于先前不考虑组合性或不确定性的最先进方法。
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.