Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking
This addresses the data sparsity issue in multi-domain dialogue systems, which is an incremental improvement for dialogue state tracking.
The paper tackles the data sparsity problem in multi-domain dialogue state tracking by proposing a context and schema fusion network that uses internal and external attention mechanisms to encode dialogue context and schema graphs. The approach achieves new state-of-the-art performance on MultiWOZ 2.0 and MultiWOZ 2.1 benchmarks.
Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is a major obstacle due to increased numbers of state candidates and dialogue lengths. To encode the dialogue context efficiently, we utilize the previous dialogue state (predicted) and the current dialogue utterance as the input for DST. To consider relations among different domain-slots, the schema graph involving prior knowledge is exploited. In this paper, a novel context and schema fusion network is proposed to encode the dialogue context and schema graph by using internal and external attention mechanisms. Experiment results show that our approach can obtain new state-of-the-art performance of the open-vocabulary DST on both MultiWOZ 2.0 and MultiWOZ 2.1 benchmarks.