论文标题
基于状态图的多域对话状态跟踪
Multi-Domain Dialogue State Tracking based on State Graph
论文作者
论文摘要
我们使用开放词汇研究了多域对话状态跟踪（DST）的问题，该问题旨在从对话中提取状态。现有的方法通常将先前的对话状态与对话历史记录相连，作为双向变压器编码器的输入。他们依靠变压器的自我发挥机制来连接其中的令牌。但是，可能会注意虚假联系，从而导致错误的推断。在本文中，我们建议构建一个对话状态图，其中域，插槽和值从上一个对话状态正确连接。通过训练，图节点和边缘嵌入可以编码域域，插槽插槽和域插槽之间的共发生关系，从而反映了一般对话中强的过渡路径。用关系GCN编码的状态图融合到变压器编码中。实验结果表明，我们的方法在任务上实现了新的最新技术，同时保持有效的效率。它的表现优于现有的开放式DST方法。
We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary, which aims to extract the state from the dialogue. Existing approaches usually concatenate previous dialogue state with dialogue history as the input to a bi-directional Transformer encoder. They rely on the self-attention mechanism of Transformer to connect tokens in them. However, attention may be paid to spurious connections, leading to wrong inference. In this paper, we propose to construct a dialogue state graph in which domains, slots and values from the previous dialogue state are connected properly. Through training, the graph node and edge embeddings can encode co-occurrence relations between domain-domain, slot-slot and domain-slot, reflecting the strong transition paths in general dialogue. The state graph, encoded with relational-GCN, is fused into the Transformer encoder. Experimental results show that our approach achieves a new state of the art on the task while remaining efficient. It outperforms existing open-vocabulary DST approaches.
