AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
This addresses the problem of limited output diversity in task-oriented dialog systems for users and developers, representing an incremental improvement over existing methods.
The authors tackled the problem of improving dialog management and lexical diversity in task-oriented dialog systems by introducing AARGH, an end-to-end model combining retrieval and generation. On the MultiWOZ dataset, their approach produced more diverse outputs while maintaining or improving state tracking and context-to-response generation performance compared to state-of-the-art baselines.
We introduce AARGH, an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog management and lexical diversity of outputs. The model features a new response selection method based on an action-aware training objective and a simplified single-encoder retrieval architecture which allow us to build an end-to-end retrieval-enhanced generation model where retrieval and generation share most of the parameters. On the MultiWOZ dataset, we show that our approach produces more diverse outputs while maintaining or improving state tracking and context-to-response generation performance, compared to state-of-the-art baselines.