Pith. sign in

REVIEW

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.05932 v1 pith:2UTKFE3E submitted 2023-02-12 cs.CL

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking

classification cs.CL
keywords dialoguein-contextexemplarsmodelmodelstasksimprovelanguage
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplars to guide output generation. However, for more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial, leading to unstable results. Furthermore, building in-context exemplars for dialogue tasks is difficult because conversational contexts are long while model input lengths are relatively short. To overcome these issues we first adapt a meta-learning scheme to the dialogue domain which stabilizes the ability of the model to perform well under various prompts. We additionally design a novel training method to improve upon vanilla retrieval mechanisms to find ideal in-context examples. Finally, we introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query. In effect, we are able to achieve highly competitive results for few-shot DST on MultiWOZ.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.