# Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems

arXiv: https://arxiv.org/abs/2004.04305 · HTML: https://mlsanity.com/paper/2004.04305/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 9 of 9)

- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting](https://mlsanity.com/paper/2305.09067/) (2023)
- [Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System](https://mlsanity.com/paper/2205.04006/) (2022)
- [Toward Self-learning End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/2201.06849/) (2022)
- [Conversational Tree Search: A New Hybrid Dialog Task](https://mlsanity.com/paper/2303.10227/) (2023)
- [Semi-supervised Interactive Intent Labeling](https://mlsanity.com/paper/2104.13406/) (2021)
- [Towards a Zero-Data, Controllable, Adaptive Dialog System](https://mlsanity.com/paper/2403.17582/) (2024)
- [SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching](https://mlsanity.com/paper/2110.11514/) (2021)
- [Conditional Teaching Size](https://mlsanity.com/paper/2107.07038/) (2021)

## Abstract (arXiv)

Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows. While dialog flows are intuitively interpretable and good for simple scenarios, they fall short of performance in terms of the flexibility needed to handle complex dialogs. On the other hand, purely machine-learned models can handle complex dialogs, but they are considered to be black boxes and require large amounts of training data. In this demonstration, we showcase Conversation Learner, a machine teaching tool for building dialog managers. It combines the best of both approaches by enabling dialog authors to create a dialog flow using familiar tools, converting the dialog flow into a parametric model (e.g., neural networks), and allowing dialog authors to improve the dialog manager (i.e., the parametric model) over time by leveraging user-system dialog logs as training data through a machine teaching interface.