COGS中的结构泛化：超标注（几乎）是你所需的一切
Structural generalization in COGS: Supertagging is (almost) all you need
AI总结：
本文扩展神经图语义解析框架，提出配价约束超标注、图预测归约及增量早停策略，在COGS数据集上显著提升结构泛化能力。
摘要：
在许多自然语言处理应用中，神经网络在分布外样本上泛化失败。特别是，最近的多个语义解析数据集揭示了神经网络在需要组合泛化时的重大局限。在本工作中，我们从多个方面扩展了一个基于神经图的语义解析框架以缓解此问题。值得注意的是，我们提出：(1) 引入带有配价约束的超标注步骤，表达为整数线性规划；(2) 将图预测问题归约为最大匹配问题；(3) 设计增量早停训练策略以防止过拟合。实验表明，我们的方法在COGS数据集（一个已知极具挑战性的组合泛化基准）上显著提升了需要结构泛化的样本的结果。总体而言，结果证实结构约束对语义解析的泛化非常重要。
英文摘要：
In many Natural Language Processing applications, neural networks have been found to fail to generalize on out-of-distribution examples. In particular, several recent semantic parsing datasets have put forward important limitations of neural networks in cases where compositional generalization is required. In this work, we extend a neural graph-based semantic parsing framework in several ways to alleviate this issue. Notably, we propose: (1) the introduction of a supertagging step with valency constraints, expressed as an integer linear program; (2) a reduction of the graph prediction problem to the maximum matching problem; (3) the design of an incremental early-stopping training strategy to prevent overfitting. Experimentally, our approach significantly improves results on examples that require structural generalization in the COGS dataset, a known challenging benchmark for compositional generalization. Overall, our results confirm that structural constraints are important for generalization in semantic parsing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
