SEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection
This addresses the challenge of selecting appropriate responses in task-oriented dialogue systems, offering a domain-specific improvement for better system performance.
The paper tackled the problem of dialogue response selection by proposing SEntNet, a model that accounts for different information sources like user utterances and knowledge bases, achieving 91.0% accuracy on Dialog bAbI and 41.2% on DSTC2, with improvements of 4.7% and 2.4% over prior work.
Dialogue response selection is an important part of Task-oriented Dialogue Systems (TDSs); it aims to predict an appropriate response given a dialogue context. Obtaining key information from a complex, long dialogue context is challenging, especially when different sources of information are available, e.g., the user's utterances, the system's responses, and results retrieved from a knowledge base (KB). Previous work ignores the type of information source and merges sources for response selection. However, accounting for the source type may lead to remarkable differences in the quality of response selection. We propose the Source-aware Recurrent Entity Network (SEntNet), which is aware of different information sources for the response selection process. SEntNet achieves this by employing source-specific memories to exploit differences in the usage of words and syntactic structure from different information sources (user, system, and KB). Experimental results show that SEntNet obtains 91.0% accuracy on the Dialog bAbI dataset, outperforming prior work by 4.7%. On the DSTC2 dataset, SEntNet obtains an accuracy of 41.2%, beating source unaware recurrent entity networks by 2.4%.