Dialogue State Tracking with a Language Model using Schema-Driven Prompting
Citations Over TimeTop 10% of 2021 papers
Abstract
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of indomain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: Multi-WOZ 2.1 and M2M. The data and code will be available at https://github.com/ chiahsuan156/DST-as-Prompting.
Related Papers
- → Handling an inconsistently coded categorical variable in a longitudinal dataset with cat2cat(2023)1 cited
- STDDIFF: Stata module to compute Standardized differences for continuous and categorical variables(2016)
- → A new method of discrimination on qualitative variables : Categorical multiblock linear discriminant analysis(2017)
- → Modeling Categorical Factors with Two Levels(1998)