mlsanityData to 7 Oct 2026

AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models

arXiv 2102.05126 ↗First posted 9 Feb 2021cs.CL cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or diversity. To address these issues, we introduce modified training objectives for language model finetuning, and we employ massive data augmentation via back-translation to increase the diversity of the training data. We further examine the possibilities of combining data from multiples sources to improve performance on the target dataset. We carefully evaluate our contributions with both human and automatic methods. Our model substantially outperforms the baseline on the MultiWOZ data and shows competitive performance with state of the art in both automatic and human evaluation.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

28 of 48 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  9. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  10. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  11. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  12. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
16 more
  1. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
  2. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  3. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  4. 2019Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Trainingcited by 110
  5. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  6. 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
  7. 2020ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systemscited by 52
  8. 2020Overview of the Ninth Dialog System Technology Challenge: DSTC9cited by 49
  9. 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
  10. 2020Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialogcited by 37
  11. 2019Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answeringcited by 33
  12. 2020LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimizationcited by 30
  13. 2015Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Rerankingcited by 17
  14. 2019Improving Robustness of Task Oriented Dialog Systemscited by 15
  15. 2020ELITR Non-Native Speech Translation at IWSLT 2020cited by 5
  16. 2020Shape of synth to come: Why we should use synthetic data for English surface realizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 10; 2024: 7; 2025: 3; 2026: 3.

31 papers.

Sort:

By area:

  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 166
  3. 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
  4. 2023Are LLMs All You Need for Task-Oriented Dialogue?cited by 52
  5. 2022Weakly Supervised Data Augmentation Through Prompting for Dialogue Understandingcited by 32
  6. 2025Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunitiescited by 21
  7. 2023Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularizationcited by 17
  8. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
  9. 2024Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Datasetcited by 15
  10. 2022Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Taskcited by 8
  11. 2024Are LLMs Robust for Spoken Dialogues?cited by 7
  12. 2024Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialoguecited by 7
19 more
  1. 2024PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Modelscited by 6
  2. 2022Dialogue Term Extraction using Transfer Learning and Topological Data Analysiscited by 5
  3. 2023InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systemscited by 5
  4. 2024LLM-based Frameworks for API Argument Filling in Task-Oriented Conversational Systemscited by 4
  5. 2021End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Managementcited by 3
  6. 2022Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?cited by 3
  7. 2022Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Modelcited by 1
  8. 2022UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogscited by 1
  9. 2023LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systemscited by 1
  10. 2024TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Samplingcited by 1
  11. 2026Towards Better RL Training Data Utilization via Second-Order Rolloutcited by 1
  12. 2023Understanding Emotion Valence is a Joint Deep Learning Taskcited by 0
  13. 2023Curricular Transfer Learning for Sentence Encoded Taskscited by 0
  14. 2023Lexical Entrainment for Conversational Systemscited by 0
  15. 2024Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systemscited by 0
  16. 2025MonoTODia: Translating Monologue Requests to Task-Oriented Dialoguescited by 0
  17. 2025Collaborative and Proactive Management of Task-Oriented Conversationscited by 0
  18. 2026LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoningcited by 0
  19. 2026Extracting Training Dialogue Data from Large Language Model based Task Botscited by 0