Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues
Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues
复制标题
DOI：
10.1145/3397481.3450653
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Kazunori Komatani;Yuma Fujioka;Keisuke Nakashima;Katsuhiko Hayashi;Mikio Nakano
中科院分区：
文献类型：
--
作者：
Kazunori Komatani;Yuma Fujioka;Keisuke Nakashima;Katsuhiko Hayashi;Mikio Nakano
在某个领域建立完美的知识库实际上是不可能的，因此对话系统通过与用户的自然语言对话来获取知识以增强不完善的知识库是有效的。本文提出了一种当使用知识图作为知识库时为此类知识获取选择问题的框架。该框架使用知识图补全（KGC）来预测可能正确的新链接，并根据 KGC 分数选择问题。该框架的问题之一是可能会选择内容不正确的问题，这通常发生在链接预测性能较低的情况下，这会降低用户参与对话的意愿。为了缓解这个问题，本文对 KGC 训练提出了两个修改：1）创建具有图中实体名称子串的伪实体，以便名称共享子串的实体连接起来；2）限制负采样的范围。我们进行的基于交叉验证的实验表明，这些修改提高了 KGC 性能。我们还通过众包进行了一项用户研究，以调查对预测链接正确性的主观看法。结果表明，经过修改训练的模型能够避免内容不正确的问题。
Building a perfect knowledge base in a certain domain is practically impossible, so it is effective for dialogue systems to acquire knowledge for enhancing an imperfect knowledge base through natural language dialogues with users. This paper proposes a framework for selecting questions for such knowledge acquisition when a knowledge graph is used as the knowledge base. The framework uses knowledge graph completion (KGC) for predicting new links that are likely to be correct and selects questions on the basis of the KGC scores. One of the problems with this framework is that questions with incorrect content might be selected, which often occurs when the link prediction performance is low, and this would reduce the users’ willingness to engage in dialogues. To alleviate this problem, this paper presents two modifications to the KGC training: 1) creating pseudo entities having substrings of the names of the entities in the graph so that the entities whose names share substrings are connected and 2) limiting the range of negative sampling. Cross validation-based experiments we conducted showed that these modifications improved KGC performance. We also conducted a user study with crowdsourcing to investigate the subjective perception of the correctness of the predicted links. The results suggest that the model trained with the modifications is capable of avoiding questions with incorrect content.