Tracking the progress in user simulator of dialogue system.
| id | Name | Year | Conf/Jour | Type |
|---|---|---|---|---|
| 1997 | ||||
| 1 | User modeling for spoken dialogue system evaluation | 1997 | ASRU | statistical-based |
| 2000 | ||||
| 1 | A stochastic model of human-machine interaction for learning dialog strategies | 2000 | IEEE Transactions on speech and audio processing | statistical-based |
| 2 | Probabilistic simulation of human-machine dialogues | 2000 | ICASSP | statistical-based |
| 2001 | ||||
| 1 | Corpus-based dialogue simulation for automatic strategy learning and evaluation | 2001 | NAACL Workshop on Adaptation in Dialogue Systems | statistical-based |
| 2003 | ||||
| 1 | Automatic design of spoken dialogue systems | 2003 | PhD thesis | statistical-based |
| 2004 | ||||
| 1 | A Framework for Unsupervised Learning of Dialogue Strategies | 2004 | PhD thesis | statistical-based |
| 2005 | ||||
| 1 | Learning user simulations for information state update dialogue systems | 2005 | INTERSPEECH | statistical-based |
| 2 | Quantitative evaluation of user simulation techniques for spoken dialogue systems | 2005 | SIGDIAL | Evaluation |
| 3 | Human-computer dialogue simulation using hidden Markov models | 2005 | ASRU | statistical-based |
| 2006 | ||||
| 1 | Testing the performance of spoken dialogue systems by means of an artificially simulated user | 2006 | Artificial Intelligence Review | statistical-based |
| 2 | Learning more effective dialogue strategies using limited dialogue move features | 2006 | ACL | statistical-based |
| 3 | A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies | 2006 | The Knowledge Engineering Review | Review |
| 4 | A probabilistic framework for dialog simulation and optimal strategy learning | 2006 | TASLP | statistical-based |
| 2007 | ||||
| 1 | Agenda-based user simulation for bootstrapping a pomdp dialogue system | 2007 | NAACL | agenda-based |
| 2009 | ||||
| 1 | The hidden agenda user simulation model | 2009 | TASLP | agenda-based |
| 2 | Data-driven user simulation for automated evaluation of spoken dialog systems | 2009 | Computer Speech & Language | |
| 2011 | ||||
| 1 | User Simulation in Dialogue Systems using Inverse Reinforcement Learning | 2011 | INTERSPEECH | Inverse RL-based |
| 2012 | ||||
| 1 | Assessment of user simulators for spoken dialogue systems by means of subspace multidimensional clustering | 2012 | INTERSPEECH | Evaluation |
| 2 | Statistical User Simulation for Spoken Dialogue Systems: What for, Which Data, Which Future? | 2012 | SDCTD | Review |
| 3 | Data-Driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational Interfaces | 2012 | Book | Review |
| 4 | Behavior Specific User Simulation in Spoken Dialogue Systems | 2012 | ITG Conference on Speech Communication | Inverse RL-based |
| 5 | An Unsupervised Approach to User Simulation: Toward Self-Improving Dialog Systems | 2012 | SIGDIAL | statistical-based |
| 2013 | ||||
| 1 | A survey on metrics for the evaluation of user simulations | 2013 | The Knowledge Engineering Review | Evaluation |
| 2016 | ||||
| 1 | A sequence-to-sequence model for user simulation in spoken dialogue systems | 2016 | INTERSPEECH | Seq2Seq-based |
| 2 | Labeled data generation with encoderdecoder LSTM for semantic slot filling | 2016 | INTERSPEECH | data augmentation |
| 2017 | ||||
| 1 | End-to-End Task-Completion Neural Dialogue Systems | 2017 | IJCNLP | agenda-based |
| 2 | A User Simulator for Task-Completion Dialogues | 2017 | arxiv | agenda-based; Tool/Framework |
| 3 | Iterative policy learning in end-to-end trainable task-oriented neural dialog models | 2017 | ASRU | Multi-Agent |
| 4 | Learning Robust Dialog Policies in Noisy Environments | 2017 | 1st Workshop on Conversational AI at NIPS | Noisy; TOD Error recovery |
| 5 | Collaboration-based User Simulation for Goal-oriented Dialog Systems | 2017 | 1st Workshop on Conversational AI at NIPS | collaboration-based; diversify |
| 6 | PyDial: A Multi-domain Statistical Dialogue System Toolkit | 2017 | ACL | Tool/Framework; Multi-domain |
| 7 | Sequence to sequence modeling for user simulation in dialog systems | 2017 | INTERSPEECH | Seq2Seq-based |
| 2018 | ||||
| 1 | User Modeling for Task Oriented Dialogues | 2018 | SLT | Seq2Seq-based |
| 2 | Building a Conversational Agent Overnight with Dialogue Self-Play | 2018 | NAACL | agenda-based; Tool/Framework |
| 3 | Sequence-to-sequence data augmentation for dialogue language understanding | 2018 | COLING | data augmentation |
| 4 | Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems | 2018 | SIGDIAL | Seq2Seq-based |
| 5 | Zero-shot dialog generation with cross-domain latent actions | 2018 | SIGDIAL | data augmentation |
| 6 | Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning | 2018 | NAACL | agenda-based; Tool/Framework |
| 7 | A User Simulator Architecture for Socially-Aware Conversational Agents | 2018 | IVA | Special domain |
| 8 | Regularized Neural User Model for Goal-Oriented Spoken Dialogue Systems | 2018 | IWSDS | Seq2Seq-based |
| 9 | Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning | 2018 | ACL | Multi-Agent |
| 10 | Discriminative deep Dyna-q: Robust planning for dialogue policy learning | 2018 | EMNLP | Multi-Agent |
| 2019 | ||||
| 1 | ConvLab: Multi-Domain End-to-End Dialog System Platform | 2019 | ACL | Tool/Framework |
| 2 | A Corpus-free State2Seq User Simulator for Task-oriented Dialogue | 2019 | CCL | Seq2Seq-based;Corpus-free |
| 3 | Graph Neural Net-Based User Simulator | 2019 | CCL | Seq2Seq-based;GUS |
| 4 | How to Build User Simulators to Train RL-based Dialog Systems | 2019 | EMNLP | Tool/Framework; Evaluation |
| 5 | Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection | 2019 | IJCAI | Diverse Responses |
| 6 | Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning | 2019 | SIGDIAL | Multi-Agent |
| 7 | Switch-Based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning | 2019 | AAAI | Multi-Agent |
| 2020 | ||||
| 1 | Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems | 2020 | EMNLP-findings | data augmentation |
| 2 | Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation | 2020 | EMNLP | data augmentation |
| 3 | Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition | 2020 | ACL | Multi-Agent |
| 4 | ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems | 2020 | ACL | Tool/Framework |
| 5 | Deep Reinforcement Learning for Dialogue Systems with Dynamic User Goals | 2020 | 学位论文 | Target transformation |
| 6 | Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions | 2020 | EMNLP | data augmentation |
| 7 | Towards Emotion-Aware User Simulator for Task-Oriented Dialogue | 2020 | arxiv | |
| 8 | Recent Advances and Challenges in Task-oriented Dialog System | 2020 | SCIENCE CHINA Technological Science | Review |
| 9 | Learning Goal-oriented Dialogue Policy with opposite Agent Awareness | 2020 | AACL | |
| 10 | Evaluating Conversational Recommender Systems via User Simulation | 2020 | KDD | Conversational Recommender Systems |
| 11 | Knowledge Graph Grounded Goal Planning for Open-Domain Conversation Generation | 2020 | AAAI | Multi-turn Open-Domain Conversation Generation |
| 12 | Discovering Dialog Structure Graph for Open-Domain Dialog Generation | 2020 | arxiv | Open-Domain Conversation Generation |
| 13 | Recipes for Building an Open-Domain Chatbot | 2020 | EACL | Open-Domain Conversation Generation |
| 2021 | ||||
| 1 | Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play | 2021 | arxiv | model-based |
| 2 | Transferable Dialogue Systems and User Simulators | 2021 | ACL | model-based |
| 3 | High-Quality Diversification for Task-Oriented Dialogue Systems | 2021 | ACL-findings | Diversify |
| 4 | Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems | 2021 | SIGDIAL | Seq2Seq-based |
| 5 | Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems | 2021 | NAACL | |
| 6 | A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition | 2021 | EMNLP | Multi-Agent |
| 7 | Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions | 2021 | EMNLP-findings | data augmentation |
| 8 | Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems | 2021 | SIGIR | TOD Evaluation |
| 2022 | ||||
| State of the Art of User Simulation approaches for conversational information retrieval | 2022 | SIM4IR | Conversational IR | |
| Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems | 2022 | arxiv | Evaluation | |
| Opponent Modeling in Negotiation Dialogues by Related Data Adaptation | 2022 | NAACL-findings | ||
| Evaluating Mixed-initiative Conversational Search Systems via User Simulation | 2022 | WSDM | Conversational Search Systems | |
| Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems | 2022 | SIGIR | Conversational Recommender Systems; TOD Error recovery | |
| SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues | 2022 | ACL | ||
| User Behavior Simulation for Search Result Re-ranking | 2022 | ACM Transactions on Information Systems | Search Result Re-ranking |