Augmenting End-to-End Dialog Systems with Commonsense Knowledge
This addresses the problem of making conversational agents more engaging and natural for users, though it is incremental as it builds on existing retrieval-based methods.
The paper tackled the challenge of integrating commonsense knowledge into end-to-end dialog systems to improve response selection in open-domain conversations, and found that knowledge-augmented models outperformed knowledge-free ones in automatic evaluations.
Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human responses in an interesting and engaging way, commonsense knowledge has to be integrated into the model effectively. In this paper, we investigate the impact of providing commonsense knowledge about the concepts covered in the dialog. Our model represents the first attempt to integrating a large commonsense knowledge base into end-to-end conversational models. In the retrieval-based scenario, we propose the Tri-LSTM model to jointly take into account message and commonsense for selecting an appropriate response. Our experiments suggest that the knowledge-augmented models are superior to their knowledge-free counterparts in automatic evaluation.