Improving Dialogue State Tracking by Discerning the Relevant Context
This work addresses a specific bottleneck in dialogue state tracking for conversational AI systems, offering incremental improvements in accuracy.
The paper tackles the problem of distinguishing relevant dialogue history in dialogue state tracking by proposing a framework that identifies context based on slot-value changes and weighted system utterances, improving joint goal accuracy by 2.75% on WoZ 2.0 and 2.36% on MultiWoZ 2.0 restaurant domain datasets over the previous state-of-the-art.
A typical conversation comprises of multiple turns between participants where they go back-and-forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user's goal by processing the current utterance. However, in many turns, users implicitly refer to the previous goal, necessitating the use of relevant dialogue history. Nonetheless, distinguishing relevant history is challenging and a popular method of using dialogue recency for that is inefficient. We, therefore, propose a novel framework for DST that identifies relevant historical context by referring to the past utterances where a particular slot-value changes and uses that together with weighted system utterance to identify the relevant context. Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance. Empirical analyses show that our method improves joint goal accuracy by 2.75% and 2.36% on WoZ 2.0 and MultiWoZ 2.0 restaurant domain datasets respectively over the previous state-of-the-art GLAD model.