Knowledge grounded dialogue system is designed to generate responses that convey information from given knowledge documents. However, it's a challenge for the current Seq2Seq model to acquire knowledge from complex documents and integrate it to perform correct responses without the aid of an explicit semantic structure. To address these issues, we present a novel graph structure, Ground Graph ($G^2$), which models the semantic structure of both dialogue contexts and knowledge documents to facilitate knowledge selection and integration for the task. Besides, a Ground Graph Aware Transformer ($G^2AT$) is proposed to enhance knowledge grounded response generation. Empirical results show that our proposed model outperforms previous state-of-the-art methods with more than 10\% and 20\% gains on response generation and factual consistency. Furthermore, our structure-aware approach shows excellent generalization ability in resource-limited situations.
翻译:以知识为基础的对话系统旨在产生从特定知识文件传递信息的反应,然而,对于目前的Seq2Seqeq模式来说,从复杂的文件中获取知识并将之整合,以便在没有明确的语义结构帮助的情况下进行正确的反应,这是一项挑战。为了解决这些问题,我们提出了一个新型的图表结构,即“地面图”(G2$),它模拟了对话背景和知识文件的语义结构,以便利为这项任务选择和整合知识。此外,还提议了一个“地面图认知变异器”(G2$G2AT$),以加强基于知识的响应生成。经验性结果显示,我们提议的模型在反应生成和事实一致性方面比以往的先进方法高出了10%和20%的收益。此外,我们的结构认知方法显示,在资源有限的情况下,具有极好的普及能力。