Aggregate question answering essentially returns answers for given questions by obtaining query graphs with unique dependencies between values and corresponding objects. Word order dependency, as the key to uniquely identify dependency of the query graph, reflects the dependencies between the words in the question. However, due to the semantic gap caused by the expression difference between questions encoded with word vectors and query graphs represented with logical formal elements, it is not trivial to match the correct query graph for the question. Most existing approaches design more expressive query graphs for complex questions and rank them just by directly calculating their similarities, ignoring the semantic gap between them. In this paper, we propose a novel Structure-sensitive Semantic Matching(SSM) approach that learns aligned representations of dependencies in questions and query graphs to eliminate their gap. First, we propose a cross-structure matching module to bridge the gap between two modalities(i.e., textual question and query graph). Then, we propose an entropy-based gated AQG filter to remove the structural noise caused by the uncertainty of dependencies. Finally, we present a two-channel query graph representation that fuses the semantics of abstract structure and grounding content of the query graph explicitly. Experimental results show that SSM could learn aligned representations of questions and query graphs to eliminate the gaps between their dependencies, and improves up to 12% (F1 score) on aggregation questions of two benchmark datasets.

聚合问答本质上是通过获取在值和对应对象之间具有唯一依赖关系的查询图来返回给定问题的答案。词序依赖，作为唯一标识查询图依赖关系的关键，反映了问题中单词之间的依赖关系。然而，由于用词向量编码的问题和用逻辑形式元素表示的查询图之间的表达差异导致的语义差距，为问题匹配正确的查询图并非易事。大多数现有方法为复杂问题设计更具表现力的查询图，并仅通过直接计算它们的相似性来对它们进行排名，而忽略它们之间的语义差距。在本文中，我们提出了一种新颖的结构敏感语义匹配（SSM）方法，该方法学习问题和查询图中依赖关系的对齐表示，以消除它们之间的差距。首先，我们提出了一个跨结构匹配模块来弥合两种模式之间的差距（即，文本问题和查询图）。然后，我们提出了一种基于熵的门控 AQG 滤波器来消除由依赖关系的不确定性引起的结构噪声。最后，我们提出了一种双通道查询图表示，它明确地融合了抽象结构的语义和查询图的基础内容。实验结果表明，SSM 可以学习问题和查询图的对齐表示，以消除它们之间的依赖关系，并在两个基准数据集的聚合问题上提高高达 12%（F1 分数）。我们提出了一种双通道查询图表示，它明确地融合了抽象结构的语义和查询图的基础内容。实验结果表明，SSM 可以学习问题和查询图的对齐表示，以消除它们之间的依赖关系，并在两个基准数据集的聚合问题上提高高达 12%（F1 分数）。我们提出了一种双通道查询图表示，它明确地融合了抽象结构的语义和查询图的基础内容。实验结果表明，SSM 可以学习问题和查询图的对齐表示，以消除它们之间的依赖关系，并在两个基准数据集的聚合问题上提高高达 12%（F1 分数）。