Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Pretraining the Noisy Channel Model for Task-Oriented Dialogue

About

Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses. Here we argue for the use of Bayes' theorem to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself. This approach, an instantiation of the noisy channel model, both mitigates the explaining-away effect and allows the principled incorporation of large pretrained models for the response prior. We present extensive experiments showing that a noisy channel model decodes better responses compared to direct decoding and that a two stage pretraining strategy, employing both open-domain and task-oriented dialogue data, improves over randomly initialized models.

Qi Liu, Lei Yu, Laura Rimell, Phil Blunsom• 2021

Related benchmarks

TaskDatasetResultRank
End-to-end task-oriented dialogueMultiWOZ (test)
Task Success Rate76.2
68
End-to-end Dialogue ModellingMultiWOZ 2.0 (test)
Inform Rate86.9
22
Task-oriented DialogueCamRest676 end-to-end modeling (test)
Task Success Rate85.3
18
Task-oriented DialogueSMCalFlow (test)
SacreBLEU64.29
9
Showing 4 of 4 rows

Other info

Code

Follow for update