Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Pascale Fung, Zhiguang Wang
| Challenge: | Existing continuous learning systems are not designed to add new domains and functionalities through time without incurring the high cost of retraining the whole system. |
| Approach: | They propose a first-ever continual learning benchmark for task-oriented dialogue systems . they propose 'architecture' method based on residual adapters to implement continual training . |
| Outcome: | The proposed architectural method performs better than multitask learning while being 20X faster in learning new domains. |
Similar Papers
Task-wrapped Continual Learning in Task-Oriented Dialogue Systems (2025.findings-naacl)
Copied to clipboard
| Challenge: | Continual learning is vital for task-oriented dialogue systems (ToDs), but its performance is limited by training separate adapters for each task, preventing global knowledge sharing. |
| Approach: | They propose a framework that employs task-wrapped Adapters to learn global and task-specific information through parameter sharing. |
| Outcome: | The proposed framework outperforms AdapterCL in 37 domains while using only 46% of the parameters. |
Dynamic Dialogue Policy for Continual Reinforcement Learning (2022.coling-1)
Copied to clipboard
Christian Geishauser, Carel van Niekerk, Hsien-chin Lin, Nurul Lubis, Michael Heck, Shutong Feng, Milica Gašić
| Challenge: | Continual reinforcement learning of the dialogue policy has remained unaddressed . lack of a framework with training protocols, baseline models and suitable metrics has hindered research in this direction. |
| Approach: | They propose a continual learning algorithm, baseline architectures and metrics for assessing continual reinforcement learning models. |
| Outcome: | The proposed architecture can integrate new knowledge seamlessly and achieve significant zero-shot performance when exposed to unseen domains. |
Continual Learning for Natural Language Generation in Task-oriented Dialog Systems (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing neural approaches for natural language generation are typically developed offline for specific domains. |
| Approach: | They propose a method to expand NLG knowledge incrementally to new domains . major challenge is catastrophic forgetting, meaning a model forgets the knowledge it has learned before . |
| Outcome: | The proposed method outperforms other methods by effectively mitigating catastrophic forgetting issue. |
Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods to learn consecutive tasks without forgetting how to perform previously trained problems are lacking. |
| Approach: | They propose a continual learning method which preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks. |
| Outcome: | The proposed method preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks. |
Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation (2023.eacl-srw)
Copied to clipboard
| Challenge: | Recent task-oriented dialogue systems are trained on annotated dialogues, but when domain knowledge changes, the initial model may become obsolete. |
| Approach: | They propose to use an annotated dialogue dataset to train a dialogue model for domain changes . they propose to fine-tune a generative language model on domain changes to reduce performance . |
| Outcome: | The proposed approach reduces performance by 55% by fine-tuning a generative language model on domain changes. |
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress through using reinforcement learning methods. |
| Approach: | They propose a dialogue action decoder and a simulator-free adversarial learning method to improve dialogue agent performance without using reinforcement learning. |
| Outcome: | The proposed methods achieve more stable and higher performance with fewer efforts, such as the domain knowledge required to design a user simulator and the intractable parameter tuning in reinforcement learning. |
Continual Prompt Tuning for Dialog State Tracking (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to train a model on a sequence of tasks are not efficient enough to mitigate catastrophic forgetting. |
| Approach: | They propose a parameter-efficient framework that prevents forgetting and enables knowledge transfer between tasks by learning and freezing a pre-trained model. |
| Outcome: | The proposed framework avoids forgetting and enables knowledge transfer between tasks. |
End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions (2023.emnlp-main)
Copied to clipboard
| Challenge: | End-to-end task-oriented dialogue (EToD) can generate responses in an end-to end fashion without modular training, which attracts escalating popularity. |
| Approach: | They present a systematic review of EToD and propose a unified perspective to summarize existing approaches and recent trends. |
| Outcome: | The proposed approaches can generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. |
End-to-End Learning of Task-Oriented Dialogs (N18-4)
Copied to clipboard
| Challenge: | Dissertation addresses the limitations of conventional task-oriented dialog systems . conventions of such systems include a complex pipeline and dialog state tracking . |
| Approach: | They propose a neural network based dialog system that can robustly track dialog state . they propose offline training and online interactive learning methods to improve efficiency . |
| Outcome: | The proposed system can track dialog state, interface with knowledge bases, and integrate structured query results into system responses to successfully complete task-oriented dialog. |
Continual Dialogue State Tracking via Example-Guided Question Answering (2023.emnlp-main)
Copied to clipboard
Hyundong Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Chandu, Satwik Kottur, Jing Xu, Jonathan May, Chinnadhurai Sankar
| Challenge: | Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services causes catastrophic forgetting. |
| Approach: | They propose to reformulate dialogue state tracking (DST) as a bundle of example-guided question answering tasks to minimize the task shift between services. |
| Outcome: | The proposed model achieves state-of-the-art performance on DST continual learning metrics without relying on any complex regularization or parameter expansion methods. |