mlsanityData to 14 Oct 2026

Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task

arXiv 2208.07097 ↗First posted 15 Aug 2022cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

The adoption of pre-trained language models in task-oriented dialogue systems has resulted in significant enhancements of their text generation abilities. However, these architectures are slow to use because of the large number of trainable parameters and can sometimes fail to generate diverse responses. To address these limitations, we propose two models with auxiliary tasks for response selection - (1) distinguishing distractors from ground truth responses and (2) distinguishing synthetic responses from ground truth labels. They achieve state-of-the-art results on the MultiWOZ 2.1 dataset with combined scores of 107.5 and 108.3 and outperform a baseline with three times more parameters. We publish reproducible code and checkpoints and discuss the effects of applying auxiliary tasks to T5-based architectures.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 15 Aug 2022.

Builds on

21 of 31 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  6. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 670
  8. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  9. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  10. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  11. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  12. 2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
9 more
  1. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  2. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  3. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  4. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  5. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  6. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  7. 2019Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answeringcited by 33
  8. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
  9. 2022Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filteringcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 4; 2025: 1.

8 papers.

  1. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  2. 2023DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systemscited by 6
  3. 2023InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systemscited by 5
  4. 2024DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automatoncited by 5
  5. 2024TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Samplingcited by 1
  6. 2024Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Expertscited by 0
  7. 2024Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learningcited by 0
  8. 2025Collaborative and Proactive Management of Task-Oriented Conversationscited by 0