Answering complex questions involving multiple relations over knowledge bases is a challenging task. Many previous works rely on dependency parsing. However, errors in dependency parsing would influence their performance, in particular for long complex questions. In this paper, we propose a novel skeleton grammar to represent the high-level structure of a complex question. This lightweight formalism and its BERT-based parsing algorithm help to improve the downstream dependency parsing. To show the effectiveness of skeleton, we develop two question answering approaches: skeleton-based semantic parsing (called SSP) and skeleton-based information retrieval (called SIR). In SSP, skeleton helps to improve structured query generation. In SIR, skeleton helps to improve path ranking. Experimental results show that, thanks to skeletons, our approaches achieve state-of-the-art results on three datasets: LC-QuAD 1.0, GraphQuestions, and ComplexWebQuestions 1.1.

回答涉及知识库上多种关系的复杂问题是一项具有挑战性的任务。许多以前的工作依赖于依赖解析。然而，依赖解析中的错误会影响它们的性能，特别是对于长复杂的问题。在本文中，我们提出了一种新颖的骨架语法来表示复杂问题的高级结构。这种轻量级的形式主义及其基于 BERT 的解析算法有助于改进下游依赖解析。为了展示骨架的有效性，我们开发了两种问答方法：基于骨架的语义解析（称为SSP）和基于骨架的信息检索（称为SIR）。在SSP 中，骨架有助于改进结构化查询的生成。在SIR, 骨架有助于提高路径排名。实验结果表明，由于骨架，我们的方法在三个数据集上取得了最先进的结果：LC-QuAD 1.0、GraphQuestions 和 ComplexWebQuestions 1.1。