Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Diable: Efficient Dialogue State Tracking as Operations on Tables

Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Yassine Benajiba, Lluis Marquez

TL;DR

Diable is proposed, a new task formalisation that simplifies the design and implementation of efficient DST systems and allows one to easily plug and play large language models and robust to noisy data annotations due to the table operations approach.

Abstract

Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn. This approach is inefficient, especially when the number of slots is large and the conversation is long. We propose Diable, a new task formalisation that simplifies the design and implementation of efficient DST systems and allows one to easily plug and play large language models. We represent the dialogue state as a table and formalise DST as a table manipulation task. At each turn, the system updates the previous state by generating table operations based on the dialogue context. Extensive experimentation on the MultiWoz datasets demonstrates that Diable (i) outperforms strong efficient DST baselines, (ii) is 2.4x more time efficient than current state-of-the-art methods while retaining competitive Joint Goal Accuracy, and (iii) is robust to noisy data annotations due to the table operations approach.

Diable: Efficient Dialogue State Tracking as Operations on Tables

TL;DR

Diable is proposed, a new task formalisation that simplifies the design and implementation of efficient DST systems and allows one to easily plug and play large language models and robust to noisy data annotations due to the table operations approach.

Abstract

Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn. This approach is inefficient, especially when the number of slots is large and the conversation is long. We propose Diable, a new task formalisation that simplifies the design and implementation of efficient DST systems and allows one to easily plug and play large language models. We represent the dialogue state as a table and formalise DST as a table manipulation task. At each turn, the system updates the previous state by generating table operations based on the dialogue context. Extensive experimentation on the MultiWoz datasets demonstrates that Diable (i) outperforms strong efficient DST baselines, (ii) is 2.4x more time efficient than current state-of-the-art methods while retaining competitive Joint Goal Accuracy, and (iii) is robust to noisy data annotations due to the table operations approach.
Paper Structure (46 sections, 2 equations, 2 figures, 12 tables)

This paper contains 46 sections, 2 equations, 2 figures, 12 tables.

Table of Contents

  1. Introduction
  2. A Taxonomy of DST Approaches
  3. Ontology-based approaches
  4. Open-vocabulary approaches
  5. Efficient approaches
  6. Diable: Dialogue State Tracking as Operations on Tables
  7. Problem Definition
  8. The Diable Approach
  9. Representing the State as a Table
  10. State Tracking via Table Operations
  11. Experiments
  12. Datasets
  13. Evaluation
  14. Cumulative State and Efficient Baselines
  15. Results
  16. ...and 31 more sections

Figures (2)

  • Figure 1: Diable approach to DST. The figure presents the first two turns of a dialogue (user's utterances are orange, system's are green). When the conversation starts, the state table is empty. At each dialogue turn, the system outputs a table update operation (either INSERT or DELETE ), and the state is modified accordingly.
  • Figure 2: Cumulative state approach to DST. At each dialogue turn, the system outputs all the slots. Inactive slots are filled with a placeholder value ( none ).