# High-Quality Diversification for Task-Oriented Dialogue Systems

arXiv: https://arxiv.org/abs/2106.00891 · HTML: https://mlsanity.com/paper/2106.00891/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 30 of 33)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2005.00891/) (2020)
- [A User Simulator for Task-Completion Dialogues](https://mlsanity.com/paper/1612.05688/) (2016)
- [End-to-End Task-Completion Neural Dialogue Systems](https://mlsanity.com/paper/1703.01008/) (2017)
- [ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems](https://mlsanity.com/paper/2002.04793/) (2020)
- [How to Build User Simulators to Train RL-based Dialog Systems](https://mlsanity.com/paper/1909.01388/) (2019)
- [Ask the Right Questions: Active Question Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1705.07830/) (2017)
- [Learning To Simulate](https://mlsanity.com/paper/1810.02513/) (2018)
- [Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion](https://mlsanity.com/paper/1910.03262/) (2019)
- [Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog](https://mlsanity.com/paper/1908.10719/) (2019)
- [Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access](https://mlsanity.com/paper/1609.00777/) (2016)
- [Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.13656/) (2020)
- [Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints](https://mlsanity.com/paper/1809.01215/) (2018)
- [BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1711.05715/) (2017)
- [Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition](https://mlsanity.com/paper/2004.03809/) (2020)
- [Automatically Learning Data Augmentation Policies for Dialogue Tasks](https://mlsanity.com/paper/1909.12868/) (2019)
- [Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning](https://mlsanity.com/paper/1808.09442/) (2018)

## Built on by (most cited first, 3 of 3)

- [EmoUS: Simulating User Emotions in Task-Oriented Dialogues](https://mlsanity.com/paper/2306.01579/) (2023)
- [Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling](https://mlsanity.com/paper/2412.02415/) (2024)
- [An Asynchronous Updating Reinforcement Learning Framework for Task-oriented Dialog System](https://mlsanity.com/paper/2305.02718/) (2023)

## Abstract (arXiv)

Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and complete the tasks successfully. Training DRL agents with diverse dialogue trajectories prepare them well for rare user requests and unseen situations. One effective diversification method is to let the agent interact with a diverse set of learned user models. However, trajectories created by these artificial user models may contain generation errors, which can quickly propagate into the agent's policy. It is thus important to control the quality of the diversification and resist the noise. In this paper, we propose a novel dialogue diversification method for task-oriented dialogue systems trained in simulators. Our method, Intermittent Short Extension Ensemble (I-SEE), constrains the intensity to interact with an ensemble of diverse user models and effectively controls the quality of the diversification. Evaluations on the Multiwoz dataset show that I-SEE successfully boosts the performance of several state-of-the-art DRL dialogue agents.