Towards Universal Dialogue State Tracking
This addresses a scalability problem for spoken dialogue systems, offering a more universal solution, though it appears incremental as it builds on existing tracking methods.
The paper tackles the challenge of scaling dialogue state tracking to large domains by proposing StateNet, which overcomes limitations like dynamic ontology changes and slot-dependent parameters, achieving significant performance improvements over state-of-the-art approaches on two datasets.
Dialogue state tracking is the core part of a spoken dialogue system. It estimates the beliefs of possible user's goals at every dialogue turn. However, for most current approaches, it's difficult to scale to large dialogue domains. They have one or more of following limitations: (a) Some models don't work in the situation where slot values in ontology changes dynamically; (b) The number of model parameters is proportional to the number of slots; (c) Some models extract features based on hand-crafted lexicons. To tackle these challenges, we propose StateNet, a universal dialogue state tracker. It is independent of the number of values, shares parameters across all slots, and uses pre-trained word vectors instead of explicit semantic dictionaries. Our experiments on two datasets show that our approach not only overcomes the limitations, but also significantly outperforms the performance of state-of-the-art approaches.