mlsanityData to 13 Oct 2026

Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems

arXiv 2110.05221 ↗First posted 11 Oct 2021cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling. In this paper, we leverage multi-task learning techniques to train a GPT-2 based model on a more challenging dataset with multiple domains, multiple modalities, and more diversity in output formats. Using only a single model, our method achieves better performance on all sub-tasks, across domains, compared to task and domain-specific models. Furthermore, we evaluated several proposed strategies for GPT-2 based dialogue systems with comprehensive ablation studies, showing that all techniques can further improve the performance.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

15 of 21 references.

References · 15

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  2. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 761
  3. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  4. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 428
  5. 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 350
  6. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  7. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  8. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  9. 2019BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformercited by 38
  10. 2020Situated and Interactive Multimodal Conversationscited by 35
  11. 2016Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learningcited by 29
  12. 2018Multi-task learning for Joint Language Understanding and Dialogue State Trackingcited by 15
3 more
  1. 2020Goal-Oriented Multi-Task BERT-Based Dialogue State Trackercited by 8
  2. 2019SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platformcited by 5
  3. 2020Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Trackingcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmarkcited by 0