Question answering on knowledge bases (KBQA) poses a unique challenge for semantic parsing research due to two intertwined challenges: large search space and ambiguities in schema linking. Conventional ranking-based KBQA models, which rely on a candidate enumeration step to reduce the search space, struggle with flexibility in predicting complicated queries and have impractical running time. In this paper, we present ArcaneQA, a novel generation-based model that addresses both the large search space and the schema linking challenges in a unified framework with two mutually boosting ingredients: dynamic program induction for tackling the large search space and dynamic contextualized encoding for schema linking. Experimental results on multiple popular KBQA datasets demonstrate the highly competitive performance of ArcaneQA in both effectiveness and efficiency.
翻译:在知识基础(KBQA)上回答问题对语义分析研究提出了独特的挑战,因为有两个相互交织的挑战:巨大的搜索空间和方略连接中的模糊不清。基于常规排名的KBQA模型依靠候选查点步骤缩小搜索空间,在预测复杂查询时以灵活方式挣扎,运行时间不切实际。本文介绍ArcaneQA,这是一个以新一代为基础的新型模型,既解决了大型搜索空间,又将统一框架内的挑战与两个相互促进的因素联系起来:应对大型搜索空间的动态程序启动,以及化学链接的动态背景编码。多个广受欢迎的KBQA数据集的实验结果显示了ArcaneQA在有效性和效率两方面的高度竞争性表现。