mlsanityData to 14 Oct 2026

Task-Oriented Dialogue System as Natural Language Generation

arXiv 2108.13679 ↗First posted 31 Aug 2021cs.CL cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization prepossessing. However, directly applying this method heavily suffers from the dialogue entity inconsistency caused by the removal of delexicalized tokens, as well as the catastrophic forgetting problem of the pre-trained model during fine-tuning, leading to unsatisfactory performance. To alleviate these problems, we design a novel GPT-Adapter-CopyNet network, which incorporates the lightweight adapter and CopyNet modules into GPT-2 to achieve better performance on transfer learning and dialogue entity generation. Experimental results conducted on the DSTC8 Track 1 benchmark and MultiWOZ dataset demonstrate that our proposed approach significantly outperforms baseline models with a remarkable performance on automatic and human evaluations.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 31 Aug 2021.

Builds on

31 of 39 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  7. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  8. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 218
  9. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  10. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  11. 2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
  12. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
19 more
  1. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  2. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  3. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  4. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  5. 2018Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systemscited by 70
  6. 2019Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Modelscited by 53
  7. 2019Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attentioncited by 44
  8. 2019Structured Fusion Networks for Dialogcited by 40
  9. 2020Incorporating BERT into Parallel Sequence Decoding with Adapterscited by 39
  10. 2019ConvLab: Multi-Domain End-to-End Dialog System Platformcited by 29
  11. 2019The Eighth Dialog System Technology Challengecited by 25
  12. 2018Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learningcited by 21
  13. 2021Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Trackingcited by 20
  14. 2020UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialoguescited by 19
  15. 2020Non-Autoregressive Dialog State Trackingcited by 15
  16. 2019HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Trackingcited by 14
  17. 2018OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understandingcited by 13
  18. 2019Budgeted Policy Learning for Task-Oriented Dialogue Systemscited by 13
  19. 2019Teacher-Student Framework Enhanced Multi-domain Dialogue Generationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 1; 2025: 1; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Augmenting Language Models with Long-Term Memorycited by 189
  2. 2023Think, Act, and Ask: Open-World Interactive Personalized Robot Navigationcited by 31
  3. 2023Bot or Human? Detecting ChatGPT Imposters with A Single Questioncited by 26
  4. 2022Visually-Augmented Language Modelingcited by 18
  5. 2022Automatic Song Translation for Tonal Languagescited by 12
  6. 2023CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialoguecited by 12
  7. 2022Improved and Efficient Conversational Slot Labeling through Question Answeringcited by 10
  8. 2024GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognitioncited by 7
  9. 2023STEPS: A Benchmark for Order Reasoning in Sequential Taskscited by 5
  10. 2026AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agentscited by 1
  11. 2026GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistantcited by 1
  12. 2023IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systemscited by 0
2 more
  1. 2025Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialoguescited by 0
  2. 2026Impact of enriched meaning representations for language generation in dialogue tasks: A comprehensive exploration of the relevance of tasks, corpora and metricscited by 0