أصبح التعلم المستمر أمرا مهما بشكل متزايد لأنه تمكن نماذج NLP للتعلم باستمرار واكتساب المعرفة بمرور الوقت. يتم تصميم أساليب التعلم المستمرة السابقة بشكل أساسي للحفاظ على المعرفة من المهام السابقة، دون التركيز كثيرا على كيفية تعميم النماذج بشكل جيد لمهام جديدة. في هذا العمل، نقترح طريقة التنظيم القائم على معلومات المعلومات للتعلم المستمر حول تصنيف النص. أسلوبنا المقترح أولا DESENTANGLES نص مساحات مخفية في تمثيلات عامة لجميع المهام والتمثيلات الخاصة بكل مهمة فردية، ومزيد من تنظيم هذه التمثيلات بشكل مختلف بشكل أفضل تقييد المعرفة المطلوبة للتعميم. نحن نقدم أيضا مهام مساعدة بسيطة: التنبؤ بالجمل التالي وتنبؤ المهام معرف المهام، لتعلم مساحات تمثيلية عامة ومحددة أفضل. توضح التجارب التي أجريت على معايير واسعة النطاق فعالية طريقتنا في مهام تصنيف النص المستمر مع تسلسلات مختلفة وأطوال فوق خطوط الأساس الحديثة. لقد أصدرنا علنا رمزنا في https://github.com/gt-salt/idbr.
Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis on how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR.
References used
https://aclanthology.org/
Abstract Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this prob
Natural Language Processing (NLP) is increasingly relying on general end-to-end systems that need to handle many different linguistic phenomena and nuances. For example, a Natural Language Inference (NLI) system has to recognize sentiment, handle num
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can b
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair re
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task. However, merely learning the knowledge from the historical tasks, adopted by current meta-learning algorithms,