Knowledge Base Question Answering (KBQA) aims to answer natural language questions with the help of an external knowledge base. The core idea is to find the link between the internal knowledge behind questions and known triples of the knowledge base. Traditional KBQA task pipelines contain several steps, including entity recognition, entity linking, answering selection, etc. In this kind of pipeline methods, errors in any procedure will inevitably propagate to the final prediction. To address this challenge, this paper proposes a Corpus Generation - Retrieve Method (CGRM) with Pre-training Language Model (PLM) for the KBQA task. The major novelty lies in the design of the new method, wherein our approach, the knowledge enhanced T5 (kT5) model aims to generate natural language QA pairs based on Knowledge Graph triples and directly solve the QA by retrieving the synthetic dataset. The new method can extract more information about the entities from PLM to improve accuracy and simplify the processes. We test our method on NLPCC-ICCPOL 2016 KBQA dataset, and the results show that our method improves the performance of KBQA and the out straight-forward method is competitive with the state-of-the-art.
翻译:知识基础问题解答(KBQA)的目的是在外部知识库的帮助下回答自然语言问题。核心思想是找到知识库已知的三重知识背后的内部知识之间的联系。传统的KBQA任务管道包含若干步骤,包括实体识别、实体连接、回答选择等。在这种管道方法中,任何程序中的错误必然会传播到最终预测中。为了应对这一挑战,本文件提议为KBQA任务设计一种具有培训前语言模型(PLM)的Corpus Game-Retreve 方法(CGRM)。主要的新颖之处在于设计新方法,我们的方法、知识增强的T5(KT5)模型旨在产生天然语言的QA配对,以知识图三重取合成数据集直接解决QA。新的方法可以从PLM中提取更多关于实体的信息,以提高准确性和简化过程。我们用NLPCC-ICC POL 2016 KBQA数据集测试了我们的方法。结果显示,我们的方法、我们的方法是用竞争法改进了KA的绩效。