Abstract

There are two main limitations in most of the existing Knowledge Graph Question Answering (KGQA) algorithms. First, the approaches depend heavily on the structure and cannot be easily adapted to other KGs. Second, the availability and amount of additional domain-specific data in structured or unstructured formats has also proven to be critical in many of these systems. Such dependencies limit the applicability of KGQA systems and make their adoption difficult. A novel algorithm is proposed, MuHeQA, that alleviates both limitations by retrieving the answer from textual content automatically generated from KGs instead of queries over them. This new approach (1) works on one or several KGs simultaneously, (2) does not require training data what makes it is domain-independent, (3) enables the combination of knowledge graphs with unstructured information sources to build the answer, and (4) reduces the dependency on the underlying schema since it does not navigate through structured content but only reads property values. MuHeQA extracts answers from textual summaries created by combining information related to the question from multiple knowledge bases, be them structured or not. Experiments over Wikidata and DBpedia show that our approach achieves comparable performance to other approaches in single-fact questions while being domain and KG independent. Results raise important questions for future work about how the textual content that can be created from knowledge graphs enables answer extraction.

中文翻译：

---

MuHeQA：针对多个异构知识库的零样本问答

摘要

大多数现有的知识图问答（KGQA）算法有两个主要限制。首先，这些方法严重依赖于结构，并且不能轻易适应其他知识图谱。其次，事实证明，结构化或非结构化格式的附加域特定数据的可用性和数量在许多此类系统中也至关重要。这种依赖性限制了 KGQA 系统的适用性并使其难以采用。提出了一种新颖的算法 MuHeQA，它通过从 KG 自动生成的文本内容中检索答案而不是对它们进行查询来缓解这两个限制。这种新方法（1）同时作用于一个或多个知识图谱，（2）不需要训练数据，这使得它与领域无关，（3）能够将知识图与非结构化信息源相结合来构建答案，并且（ 4) 减少对底层模式的依赖，因为它不浏览结构化内容，而仅读取属性值。 MuHeQA 从文本摘要中提取答案，该文本摘要是通过组合来自多个知识库（无论是否结构化）的问题相关信息而创建的。在 Wikidata 和 DBpedia 上的实验表明，我们的方法在单事实问题上实现了与其他方法相当的性能，同时独立于领域和知识图谱。结果为未来的工作提出了重要问题，即从知识图创建的文本内容如何实现答案提取。