论文标题
通过提问和问题与问题对齐来改善复杂的知识基础问题回答
Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment
论文作者
论文摘要
复杂的知识基础问题回答可以通过将问题转换为预定义动作的序列来实现。但是，自然语言和动作序列之间存在着显着的语义和结构差距，这使得这种转换变得困难。在本文中，我们引入了一个称为Alcqa的对齐增强的复杂问题回答框架，该框架通过问题对行动对齐和问题与问题对齐来减轻这一差距。我们训练一个问题重写模型来调整问题和每个动作，并利用预验证的语言模型隐含地对齐问题和KG工件。此外，考虑到类似的问题对应于相似的动作序列，我们通过问题与问题对齐在推理阶段检索了TOP-K相似的问题 - 答案对，并提出了一种新颖的奖励指导动作序列选择策略，以从候选动作序列中进行选择。我们对CQA和WQSP数据集进行了实验，结果表明，我们的方法优于最先进的方法，并在CQA数据集上的F1度量中获得了9.88 \％的改进。我们的源代码可在https://github.com/ttttttttty/alcqa上找到。
Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions. However, there is a significant semantic and structural gap between natural language and action sequences, which makes this conversion difficult. In this paper, we introduce an alignment-enhanced complex question answering framework, called ALCQA, which mitigates this gap through question-to-action alignment and question-to-question alignment. We train a question rewriting model to align the question and each action, and utilize a pretrained language model to implicitly align the question and KG artifacts. Moreover, considering that similar questions correspond to similar action sequences, we retrieve top-k similar question-answer pairs at the inference stage through question-to-question alignment and propose a novel reward-guided action sequence selection strategy to select from candidate action sequences. We conduct experiments on CQA and WQSP datasets, and the results show that our approach outperforms state-of-the-art methods and obtains a 9.88\% improvements in the F1 metric on CQA dataset. Our source code is available at https://github.com/TTTTTTTTy/ALCQA.
