paper-with-me

Papers

Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Framework

2024-02-18 · Peng Xing, Yinghui Li, Shirong Ma, Xinnian Liang, Haojing Huang, Yangning Li, Hai-Tao Zheng, Wenhao Jiang, Ying Shen

Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in given sentences. Recently, multi-domain CSC has gradually attracted the attention of researchers because it is more practicable. In this paper, we focus on the key flaw of the CSC model when adapting to multi-domain scenarios: the tendency to forget previously acquired knowledge upon learning new domain-specific knowledge (i.e., catastrophic forgetting). To address this, we propose a novel model-agnostic Multi-stage Knowledge Transfer (MKT) framework, which utilizes a continuously evolving teacher model for knowledge transfer in each domain, rather than focusing solely on new domain knowledge. It deserves to be mentioned that we are the first to apply continual learning methods to the multi-domain CSC task. Experiments prove the effectiveness of our proposed method, and further analyses demonstrate the importance of overcoming catastrophic forgetting for improving the model performance.

📄 PDF Abstract BibTeX arXiv:2402.11422

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningSpelling CorrectionTransfer Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Mitigating Catastrophic Forgetting in Continual Learning through Model Growth

2025-09-01 · Ege Süalp, Mina Rezaei arxiv

Catastrophic forgetting is a significant challenge in continual learning, in which a model loses prior knowledge when it is fine-tuned on new tasks. This problem is particularly critical for large language models (LLMs) …

Reading ComprehensionContinual Learning

Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation

2025-09-14 · Kerun Mi, Guoliang Kang, Guangyu Li, Lin Zhao 외 arxiv

Class-Incremental Unsupervised Domain Adaptation (CI-UDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where the sets of potential target classes appearing at different time steps are…

Unsupervised Domain Adaptation

The Importance of Robust Features in Mitigating Catastrophic Forgetting

2023-06-29 · Hikmat Khan, Nidhal C. Bouaynaya, Ghulam Rasoom

Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robus…

Adversarial RobustnessContinual Learning

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging

2024-07-11 · Anton Alexandrov, Veselin Raychev, Mark Niklas Müller, Ce Zhang 외

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adapta…

AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model

2022-11-21 · Yongyu Yan, Kui Xue, Xiaoming Shi, Qi Ye 외

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forget…

Continual PretrainingLanguage ModelingLanguage Modelling