# Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management

arXiv: https://arxiv.org/abs/2010.15411 · HTML: https://mlsanity.com/paper/2010.15411/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 13 of 13)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Structure Extraction in Task-Oriented Dialogues with Slot Clustering](https://mlsanity.com/paper/2203.00073/) (2022)
- [CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding](https://mlsanity.com/paper/2203.09982/) (2022)
- [Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation](https://mlsanity.com/paper/2306.04724/) (2023)
- [N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking](https://mlsanity.com/paper/2103.00293/) (2021)
- [GraphWOZ: Dialogue Management with Conversational Knowledge Graphs](https://mlsanity.com/paper/2211.12852/) (2022)
- [Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?](https://mlsanity.com/paper/2210.12942/) (2022)
- [From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue](https://mlsanity.com/paper/2308.12648/) (2023)
- [More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking](https://mlsanity.com/paper/2303.09905/) (2023)
- [Improving Dialogue Management: Quality Datasets vs Models](https://mlsanity.com/paper/2310.01339/) (2023)
- [A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction](https://mlsanity.com/paper/2311.16137/) (2023)
- [Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/2406.06127/) (2024)
- [MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues](https://mlsanity.com/paper/2502.17268/) (2025)

## Abstract (arXiv)

Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size considering the complexity of the dialogues. Additionally, conventional training signal inference is not suitable for non-deterministic agent behaviour, i.e. considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4%.