Schema-Guided Paradigm for Zero-Shot Dialog

Shikib Mehri, Maxine Eskenazi


Abstract
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.
Anthology ID:
2021.sigdial-1.52
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
499–508
Language:
URL:
https://aclanthology.org/2021.sigdial-1.52
DOI:
Bibkey:
Cite (ACL):
Shikib Mehri and Maxine Eskenazi. 2021. Schema-Guided Paradigm for Zero-Shot Dialog. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 499–508, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Schema-Guided Paradigm for Zero-Shot Dialog (Mehri & Eskenazi, SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.52.pdf
Video:
 https://www.youtube.com/watch?v=usZQulwdOZs
Code
 Shikib/schema_attention_model
Data
STAR