TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
- URL: http://arxiv.org/abs/2408.09857v1
- Date: Mon, 19 Aug 2024 10:01:28 GMT
- Title: TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
- Authors: Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, Xiao-Ming Wu,
- Abstract summary: We present TaSL, a novel framework for task skill localization and consolidation.
TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas.
As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks.
- Score: 14.533890076297393
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL over existing state-of-the-art methods. The source code is provided for reproducibility.
Related papers
- Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating [61.70705744491162]
Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge.
Updating LLMs involves two key tasks simultaneously: unlearning to remove unwanted knowledge and editing to incorporate new information.
We propose LOKA, a conflict-free framework for LLM updating based on a knowledge codebook.
arXiv Detail & Related papers (2025-01-31T20:48:46Z) - Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning [19.463863037999054]
In dynamic domains such as autonomous robotics and video game simulations, agents must continuously adapt to new tasks while retaining previously acquired skills.
This ongoing process, known as Continual Reinforcement Learning, presents significant challenges, including the risk of forgetting past knowledge.
We introduce HIerarchical LOW-rank Subspaces of Policies (HILOW), a novel framework designed for continual learning in offline navigation settings.
arXiv Detail & Related papers (2024-12-19T14:00:03Z) - KIF: Knowledge Identification and Fusion for Language Model Continual Learning [41.28933724210434]
We introduce a novel framework for language models, named Knowledge Identification and Fusion (KIF)
KIF segregates the model into'skill units' based on parameter dependencies, allowing for more precise control.
It employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task.
As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks.
arXiv Detail & Related papers (2024-08-09T17:44:45Z) - Rethinking and Improving Multi-task Learning for End-to-end Speech
Translation [51.713683037303035]
We investigate the consistency between different tasks, considering different times and modules.
We find that the textual encoder primarily facilitates cross-modal conversion, but the presence of noise in speech impedes the consistency between text and speech representations.
We propose an improved multi-task learning (IMTL) approach for the ST task, which bridges the modal gap by mitigating the difference in length and representation.
arXiv Detail & Related papers (2023-11-07T08:48:46Z) - Subspace Chronicles: How Linguistic Information Emerges, Shifts and
Interacts during Language Model Training [56.74440457571821]
We analyze tasks covering syntax, semantics and reasoning, across 2M pre-training steps and five seeds.
We identify critical learning phases across tasks and time, during which subspaces emerge, share information, and later disentangle to specialize.
Our findings have implications for model interpretability, multi-task learning, and learning from limited data.
arXiv Detail & Related papers (2023-10-25T09:09:55Z) - Online Continual Learning via the Knowledge Invariant and Spread-out
Properties [4.109784267309124]
Key challenge in continual learning is catastrophic forgetting.
We propose a new method, named Online Continual Learning via the Knowledge Invariant and Spread-out Properties (OCLKISP)
We empirically evaluate our proposed method on four popular benchmarks for continual learning: Split CIFAR 100, Split SVHN, Split CUB200 and Split Tiny-Image-Net.
arXiv Detail & Related papers (2023-02-02T04:03:38Z) - Beyond Not-Forgetting: Continual Learning with Backward Knowledge
Transfer [39.99577526417276]
In continual learning (CL) an agent can improve the learning performance of both a new task and old' tasks.
Most existing CL methods focus on addressing catastrophic forgetting in neural networks by minimizing the modification of the learnt model for old tasks.
We propose a new CL method with Backward knowlEdge tRansfer (CUBER) for a fixed capacity neural network without data replay.
arXiv Detail & Related papers (2022-11-01T23:55:51Z) - Continual Prompt Tuning for Dialog State Tracking [58.66412648276873]
A desirable dialog system should be able to continually learn new skills without forgetting old ones.
We present Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks.
arXiv Detail & Related papers (2022-03-13T13:22:41Z) - Bilevel Continual Learning [76.50127663309604]
We present a novel framework of continual learning named "Bilevel Continual Learning" (BCL)
Our experiments on continual learning benchmarks demonstrate the efficacy of the proposed BCL compared to many state-of-the-art methods.
arXiv Detail & Related papers (2020-07-30T16:00:23Z) - Exploring the Limits of Transfer Learning with a Unified Text-to-Text
Transformer [64.22926988297685]
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP)
In this paper, we explore the landscape of introducing transfer learning techniques for NLP by a unified framework that converts all text-based language problems into a text-to-text format.
arXiv Detail & Related papers (2019-10-23T17:37:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.