UNIQORN：基于RDF知识图谱与自然语言文本的统一问答
UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text
AI总结：
本文提出UNIQORN方法，通过微调BERT构建上下文图并利用Group Steiner Trees算法，在统一框架中实现RDF数据与文本的复杂问答，显著优于现有方法。
摘要：
基于RDF数据（如知识图谱）的问答技术已取得极大进展，许多优秀的系统能为自然语言问题或电报式查询提供精准答案。其中部分系统将文本源作为回答过程的补充证据，但无法计算出仅存在于文本中的答案。相反，IR和NLP社区已解决了基于文本的QA问题，但这些系统几乎不利用语义数据和知识。本文提出了一种针对复杂问题的方法，能够在统一框架中无缝地操作RDF数据集与文本语料库的混合体，或单独的数据源。我们的方法名为UNIQORN，通过使用微调的BERT模型从RDF数据和/或文本语料库中检索与问题相关的证据，即时构建上下文图。生成的图通常包含所有与问题相关的证据，但也包含大量噪声。UNIQORN通过一种用于Group Steiner Trees的图算法来处理此输入，从而在上下文图中识别出最佳答案候选。在包含多个实体和关系的复杂问题基准上的实验结果表明，无论是在完全训练模式下还是在零样本设置中，UNIQORN均显著优于异构QA的最先进方法。这种基于图的方法为整个回答过程提供了用户可解释的证据。
英文摘要：
Question answering over RDF data like knowledge graphs has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries. Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone. Conversely, the IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora, or individual sources, in a unified framework. Our method, called UNIQORN, builds a context graph on-the-fly, by retrieving question-relevant evidences from the RDF data and/or a text corpus, using fine-tuned BERT models. The resulting graph typically contains all question-relevant evidences but also a lot of noise. UNIQORN copes with this input by a graph algorithm for Group Steiner Trees, that identifies the best answer candidates in the context graph. Experimental results on several benchmarks of complex questions with multiple entities and relations, show that UNIQORN significantly outperforms state-of-the-art methods for heterogeneous QA - in a full training mode, as well as in zero-shot settings. The graph-based methodology provides user-interpretable evidence for the complete answering process.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
