论文标题
对话框跟踪的对话语义解析
Conversational Semantic Parsing for Dialog State Tracking
论文作者
论文摘要
我们考虑对话框跟踪（DST）的新观点，这是通过对话框估算用户目标的任务。通过将DST作为层次表示的语义解析任务制定，我们可以结合语义构图，跨域知识共享和共同参考。我们提出Treedst，这是一个27K对话的数据集，该数据集用树结构化对话框状态和系统行为注释。我们描述了带有层次表示的DST的编码器框架，该框架与最先进的DST方法相比，在插槽值对的平坦含义空间上的最新DST方法提高了20％。
We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27k conversations annotated with tree-structured dialog states and system acts. We describe an encoder-decoder framework for DST with hierarchical representations, which leads to 20% improvement over state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs.
