mlsanityData to 7 Oct 2026

ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format

arXiv 2211.17148 ↗First posted 30 Nov 2022cs.CL cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants. Existing toolkits for building TOD systems often fall short of in delivering comprehensive arrays of data, models, and experimental environments with a user-friendly experience. We introduce ConvLab-3: a multifaceted dialogue system toolkit crafted to bridge this gap. Our unified data format simplifies the integration of diverse datasets and models, significantly reducing complexity and cost for studying generalization and transfer. Enhanced with robust reinforcement learning (RL) tools, featuring a streamlined training process, in-depth evaluation tools, and a selection of user simulators, ConvLab-3 supports the rapid development and evaluation of robust dialogue policies. Through an extensive study, we demonstrate the efficacy of transfer learning and RL and showcase that ConvLab-3 is not only a powerful tool for seasoned researchers but also an accessible platform for newcomers.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 45 of its 65 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

45 of 65 references.

References · 45

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  7. 2018Experience Replay for Continual Learningcited by 1,074
  8. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  9. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  10. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  11. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  12. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
33 more
  1. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 268
  2. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 240
  3. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  4. 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 142
  5. 2017ParlAI: A Dialog Research Software Platformcited by 139
  6. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
  7. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  8. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  9. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  10. 2020Task-Oriented Dialogue as Dataflow Synthesiscited by 122
  11. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  12. 2020Continual Learning in Task-Oriented Dialogue Systemscited by 82
  13. 2017Rasa: Open Source Language Understanding and Dialogue Managementcited by 67
  14. 2020CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Datasetcited by 66
  15. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  16. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  17. 2020ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systemscited by 52
  18. 2022GODEL: Large-Scale Pre-Training for Goal-Directed Dialogcited by 50
  19. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 44
  20. 2019Structured Fusion Networks for Dialogcited by 40
  21. 2020Conversational Semantic Parsing for Dialog State Trackingcited by 40
  22. 2020LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimizationcited by 30
  23. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  24. 2019ConvLab: Multi-Domain End-to-End Dialog System Platformcited by 29
  25. 2018Zero-Shot Dialog Generation with Cross-Domain Latent Actionscited by 23
  26. 2021Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systemscited by 23
  27. 2022GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformerscited by 22
  28. 2021EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systemscited by 20
  29. 2020TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systemscited by 18
  30. 2016Conditional Generation and Snapshot Learning in Neural Dialogue Systemscited by 17
  31. 2022Dynamic Dialogue Policy for Continual Reinforcement Learningcited by 12
  32. 2021Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performancecited by 8
  33. 2022Multi-Sentence Knowledge Selection in Open-Domain Dialoguecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 5; 2025: 7; 2026: 1.

22 papers.

Sort:

  1. 2023Are LLMs All You Need for Task-Oriented Dialogue?cited by 52
  2. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  3. 2023In-Context Learning User Simulators for Task-Oriented Dialog Systemscited by 19
  4. 2023Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systemscited by 16
  5. 2023X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agentscited by 12
  6. 2023EmoUS: Simulating User Emotions in Task-Oriented Dialoguescited by 9
  7. 2024Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generationcited by 5
  8. 2025DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulationcited by 5
  9. 2022KPT: Keyword-guided Pre-training for Grounded Dialog Generationcited by 3
  10. 2023From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialoguecited by 3
  11. 2023CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogscited by 3
  12. 2024Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomingscited by 3
10 more
  1. 2024Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extractioncited by 2
  2. 2024CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialoguescited by 2
  3. 2025All Learning Has an Emotional Basis, So Does Task-Oriented Dialoguecited by 2
  4. 2025EMMM, Explain Me My Model! Explainable Machine Generated Text Detection in Dialoguescited by 2
  5. 2024DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Modelscited by 1
  6. 2025SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detectioncited by 1
  7. 2025Text-to-SQL Task-oriented Dialogue Ontology Constructioncited by 1
  8. 2025Dialogue Systems Engineering: A Survey and Future Directionscited by 0
  9. 2025Prompt reinforcing for long-term planning of large language modelscited by 0
  10. 2026Lost with a Map: Conversational State and Behavioral Reliability in Language Modelscited by 0