Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue

04/08/2022
by   Raghav Gupta, et al.
1

Building universal dialogue systems that can seamlessly operate across multiple domains/APIs and generalize to new ones with minimal supervision and maintenance is a critical challenge. Recent works have leveraged natural language descriptions for schema elements to enable such systems; however, descriptions can only indirectly convey schema semantics. In this work, we propose Show, Don't Tell, a prompt format for seq2seq modeling which uses a short labeled example dialogue to show the semantics of schema elements rather than tell the model via descriptions. While requiring similar effort from service developers, we show that using short examples as schema representations with large language models results in stronger performance and better generalization on two popular dialogue state tracking benchmarks: the Schema-Guided Dialogue dataset and the MultiWoZ leave-one-out benchmark.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/17/2023

More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking

The schema-guided paradigm overcomes scalability issues inherent in buil...
research
09/15/2021

Dialogue State Tracking with a Language Model using Schema-Driven Prompting

Task-oriented conversational systems often use dialogue state tracking t...
research
10/05/2022

Schema Encoding for Transferable Dialogue State Tracking

Dialogue state tracking (DST) is an essential sub-task for task-oriented...
research
05/11/2020

Schema-Guided Natural Language Generation

Neural network based approaches to natural language generation (NLG) hav...
research
06/15/2023

Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State Tracking

In schema-guided dialogue state tracking models estimate the current sta...
research
07/15/2022

A Flexible Schema-Guided Dialogue Management Framework: From Friendly Peer to Virtual Standardized Cancer Patient

A schema-guided approach to dialogue management has been shown in recent...
research
08/27/2020

A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset

Dialog State Tracking (DST) is one of the most crucial modules for goal-...

Please sign up or login with your details

Forgot password? Click here to reset