Contextual Slot Carryover for Disparate Schemas
This addresses scalability and schema diversity issues in large-scale multi-domain conversational AI systems, representing an incremental improvement.
The paper tackles the challenge of scaling slot-filling in multi-domain conversational systems by reformulating contextual interpretation as a decision to carryover slots from candidates and using a data-driven method for heterogeneous schemas, achieving competitive results over a strong baseline.
In the slot-filling paradigm, where a user can refer back to slots in the context during a conversation, the goal of the contextual understanding system is to resolve the referring expressions to the appropriate slots in the context. In large-scale multi-domain systems, this presents two challenges - scaling to a very large and potentially unbounded set of slot values, and dealing with diverse schemas. We present a neural network architecture that addresses the slot value scalability challenge by reformulating the contextual interpretation as a decision to carryover a slot from a set of possible candidates. To deal with heterogenous schemas, we introduce a simple data-driven method for trans- forming the candidate slots. Our experiments show that our approach can scale to multiple domains and provides competitive results over a strong baseline.