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

By Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf. 2021

148 citations recorded by the source corpus.

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 in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.

Subfields: Artificial Intelligence, Large Language Models, Dialogue & Conversational AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Caiming Xiong
  2. Luke S. Zettlemoyer
  3. Percy Liang
  4. Graham Neubig
  5. Richard Socher
  6. Noah A. Smith
  7. Mohit Bansal
  8. Jianfeng Gao

In Large Language Models

  1. Noah A. Smith
  2. Caiming Xiong
  3. Luke S. Zettlemoyer
  4. Yue Zhang
  5. Dragomir R. Radev
  6. Michihiro Yasunaga
  7. Weijia Shi
  8. Lingpeng Kong

In Dialogue & Conversational AI

  1. Caiming Xiong

Citations in the corpus