Schema-Guided Paradigm for Zero-Shot Dialog
Shikib Mehri, Maxine Eskénazi · 2021
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 F 1 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.