mlsanityData to 13 Oct 2026

Every time I fire a conversational designer, the performance of the dialog system goes down

arXiv 2109.13029 ↗First posted 27 Sep 2021cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Incorporating explicit domain knowledge into neural-based task-oriented dialogue systems is an effective way to reduce the need of large sets of annotated dialogues. In this paper, we investigate how the use of explicit domain knowledge of conversational designers affects the performance of neural-based dialogue systems. To support this investigation, we propose the Conversational-Logic-Injection-in-Neural-Network system (CLINN) where explicit knowledge is coded in semi-logical rules. By using CLINN, we evaluated semi-logical rules produced by a team of differently skilled conversational designers. We experimented with the Restaurant topic of the MultiWOZ dataset. Results show that external knowledge is extremely important for reducing the need of annotated examples for conversational systems. In fact, rules from conversational designers used in CLINN significantly outperform a state-of-the-art neural-based dialogue system.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

20 of 31 references.

References · 20

  1. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 761
  2. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  3. 2017Learning Explanatory Rules from Noisy Datacited by 210
  4. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  5. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  6. 2019Survey on Evaluation Methods for Dialogue Systemscited by 126
  7. 2016Learning End-to-End Goal-Oriented Dialogcited by 104
  8. 2020Analyzing Differentiable Fuzzy Logic Operatorscited by 100
  9. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  10. 2020Learning from Task Descriptionscited by 78
  11. 2015A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestioncited by 68
  12. 2016A User Simulator for Task-Completion Dialoguescited by 56
8 more
  1. 2019Training Neural Response Selection for Task-Oriented Dialogue Systemscited by 48
  2. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 45
  3. 2017Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learningcited by 31
  4. 2016Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learningcited by 29
  5. 2019ConvLab: Multi-Domain End-to-End Dialog System Platformcited by 29
  6. 2017Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Modelscited by 26
  7. 2020Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rulescited by 4
  8. 2020Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programmingcited by 2

Built on by

Not cited yet.