paper-with-me

홈 › Papers

NERDA-Con: Extending NER models for Continual Learning -- Integrating Distinct Tasks and Updating Distribution Shifts

2022-06-28 · Supriti Vijay, Aman Priyanshu

With increasing applications in areas such as biomedical information extraction pipelines and social media analytics, Named Entity Recognition (NER) has become an indispensable tool for knowledge extraction. However, with the gradual shift in language structure and vocabulary, NERs are plagued with distribution shifts, making them redundant or not as profitable without re-training. Re-training NERs based on Large Language Models (LLMs) from scratch over newly acquired data poses economic disadvantages. In contrast, re-training only with newly acquired data will result in Catastrophic Forgetting of previously acquired knowledge. Therefore, we propose NERDA-Con, a pipeline for training NERs with LLM bases by incorporating the concept of Elastic Weight Consolidation (EWC) into the NER fine-tuning NERDA pipeline. As we believe our work has implications to be utilized in the pipeline of continual learning and NER, we open-source our code as well as provide the fine-tuning library of the same name NERDA-Con at https://github.com/SupritiVijay/NERDA-Con and https://pypi.org/project/NERDA-Con/.

📄 PDF Abstract BibTeX arXiv:2206.14607

Code (1)

supritivijay/nerda-con 공식 구현 pytorch

Tasks

Continual Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Local vs Global continual learning

2024-07-23 · Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann

Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent years, the problem of continual learnin…

Continual Learning

Continual Training of Language Models for Few-Shot Learning

2022-10-11 · Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu 외

Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can produce even better performance for end-ta…

Continual LearningContinual PretrainingFew-Shot LearningLanguage Modelling

Fine-tuned Language Models are Continual Learners

2022-05-24 · Thomas Scialom, Tuhin Chakrabarty, Smaranda Muresan

Recent work on large language models relies on the intuition that most natural language processing tasks can be described via natural language instructions. Language models trained on these instructions show strong zero-…

Continual Learning

Three continual learning scenarios and a case for generative replay

2018-09-27 · Gido M. van de Ven, Andreas S. Tolias

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning problematic. Recently, numerous methods have been proposed for continual learning, bu…

Continual LearningLifelong learningPermuted-MNIST

Integrating Curricula with Replays: Its Effects on Continual Learning

2023-07-08 · Ren Jie Tee, Mengmi Zhang

Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning ag…

Continual LearningTransfer Learning