Schema-Guided Paradigm for Zero-Shot Dialog
This addresses the problem of zero-shot transfer learning in dialog systems for researchers and developers, representing a novel method rather than an incremental improvement.
The paper tackled the challenge of enabling dialog systems to adapt to unseen tasks and domains by proposing a schema-guided paradigm, which explicitly provides task-specific dialog policies to models, resulting in a +22 F1 score improvement in zero-shot settings over prior work.
Developing mechanisms that flexibly adapt dialog systems to unseen tasks and domains is a major challenge in dialog research. Neural models implicitly memorize task-specific dialog policies from the training data. We posit that this implicit memorization has precluded zero-shot transfer learning. To this end, we leverage the schema-guided paradigm, wherein the task-specific dialog policy is explicitly provided to the model. We introduce the Schema Attention Model (SAM) and improved schema representations for the STAR corpus. SAM obtains significant improvement in zero-shot settings, with a +22 F1 score improvement over prior work. These results validate the feasibility of zero-shot generalizability in dialog. Ablation experiments are also presented to demonstrate the efficacy of SAM.