Continual Dialogue State Tracking via Example-Guided Question Answering
This addresses the issue of continual learning in dialogue systems for developers and researchers, though it is incremental as it builds on existing methods.
The paper tackled the problem of performance degradation in dialogue state tracking when updating dialogue systems with new services, by reformulating it as example-guided question answering tasks to minimize task shift. The result was a model with 60M parameters achieving state-of-the-art performance on continual learning metrics without complex regularization or parameter expansion.
Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services. Motivated by the insight that dialogue state tracking (DST), a crucial component of dialogue systems that estimates the user's goal as a conversation proceeds, is a simple natural language understanding task, we propose reformulating it as a bundle of granular example-guided question answering tasks to minimize the task shift between services and thus benefit continual learning. Our approach alleviates service-specific memorization and teaches a model to contextualize the given question and example to extract the necessary information from the conversation. We find that a model with just 60M parameters can achieve a significant boost by learning to learn from in-context examples retrieved by a retriever trained to identify turns with similar dialogue state changes. Combining our method with dialogue-level memory replay, our approach attains state of the art performance on DST continual learning metrics without relying on any complex regularization or parameter expansion methods.