论文标题
在基于检索的聊天机器人中进行迭代参考以获取知识接地的响应选择之前进行过滤
Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots
论文作者
论文摘要
建立基于知识的基于检索的聊天机器人的挑战在于如何在其背景知识上进行对话，以及如何同时将响应候选者匹配。本文提出了一种在此任务迭代引用（FIRE）之前的名为过滤的方法。在这种方法中，首先构建了上下文过滤器和知识过滤器，该过滤器分别通过全局和双向关注得出知识感知的上下文表示和上下文感知的知识表示。此外，与对话无关的条目被知识过滤器丢弃。之后，在上下文和响应表示之间以及知识和响应表示之间进行迭代参考，以收集对响应候选者的深度匹配功能。实验结果表明，通过具有原始和修订的角色的角色 - chat数据集，FIRE的优于以前的方法大于2.8％和4.1％，而在TOP-1准确性方面，CMU_DOG数据集的利润率大于3.1％。我们还表明，通过可视化知识接地过程，火灾更容易解释。
The challenges of building knowledge-grounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously. This paper proposes a method named Filtering before Iteratively REferring (FIRE) for this task. In this method, a context filter and a knowledge filter are first built, which derive knowledge-aware context representations and context-aware knowledge representations respectively by global and bidirectional attention. Besides, the entries irrelevant to the conversation are discarded by the knowledge filter. After that, iteratively referring is performed between context and response representations as well as between knowledge and response representations, in order to collect deep matching features for scoring response candidates. Experimental results show that FIRE outperforms previous methods by margins larger than 2.8% and 4.1% on the PERSONA-CHAT dataset with original and revised personas respectively, and margins larger than 3.1% on the CMU_DoG dataset in terms of top-1 accuracy. We also show that FIRE is more interpretable by visualizing the knowledge grounding process.
