mlsanityData to 7 Oct 2026

UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogs

arXiv 2209.07239 ↗First posted 15 Sep 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error propagation and damaging the robustness of the TOD system. To bridge the gap between training and inference for multi-turn task-oriented dialogs, we propose session-level sampling which explicitly exposes the model to sampled generated content of dialog context during training. Additionally, we employ a dropout-based consistency regularization with the masking strategy R-Mask to further improve the robustness and performance of the model. The proposed UBARv2 achieves state-of-the-art performance on the standardized evaluation benchmark MultiWOZ and extensive experiments show the effectiveness of the proposed methods.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

33 of 41 references.

References · 33

  1. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  2. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  3. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  4. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  5. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  6. 2021R-Drop: Regularized Dropout for Neural Networkscited by 202
  7. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  8. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  9. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 131
  10. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  11. 2016Sequence-to-Sequence Learning as Beam-Search Optimizationcited by 126
  12. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
21 more
  1. 2015Minimum Risk Training for Neural Machine Translationcited by 114
  2. 2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
  3. 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
  4. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  5. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  6. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  7. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  8. 2020Contrastive Learning with Adversarial Perturbations for Conditional Text Generationcited by 56
  9. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  10. 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
  11. 2019Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attentioncited by 43
  12. 2019Structured Fusion Networks for Dialogcited by 40
  13. 2021Transferable Dialogue Systems and User Simulatorscited by 35
  14. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
  15. 2020LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimizationcited by 30
  16. 2020Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue Systemcited by 28
  17. 2020Multi-Domain Dialogue Acts and Response Co-Generationcited by 26
  18. 2022BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialogcited by 20
  19. 2020UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialoguescited by 19
  20. 2018Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Mattercited by 18
  21. 2021Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memorycited by 8

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schemacited by 3