Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering. However, this paradigm constrains retrieved knowledge in local subgraphs and discards more diverse triplets buried in KGs that are disconnected but useful for question answering. In this paper, we propose a simple yet effective method to first retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models. Extensive results on both CommonsenseQA and OpenbookQA datasets show that our method can outperform state-of-the-art up to 4.6% absolute accuracy.

翻译：复杂问题的解答通常需要对知识图谱进行推理。现有最优方法往往利用问题中的实体检索局部子图，随后将其输入图编码器（如图神经网络）以建模局部结构，并整合到语言模型中进行问答。然而，这种范式将检索知识局限于局部子图，丢弃了知识图谱中虽无直接关联但对问答具有价值的更多样化三元组。本文提出一种简洁有效的方法：首先从知识图谱中检索最相关三元组，对其进行重排序，随后将其与问题拼接后输入语言模型。在CommonsenseQA和OpenbookQA数据集上的大量实验表明，本方法在绝对准确率上可比现有最优方法提升最高4.6%。