পদ্ধতির তুলনা করুন

	দুর্বলভাবে তত্ত্বাবধানে পাঠ্য সংক্ষিপ্তকরণ	স্ব-পর্যবেক্ষণাধীন শিখন
ক্ষেত্র	গভীর শিখন	যন্ত্র শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	2015–2020	2018–2020
প্রবর্তক	Multiple independent research groups (NLP community, 2010s–2020s)	LeCun, Y. and community (formalized ~2018–2020)
ধরন	Semi-supervised / weakly supervised NLP training paradigm	Representation learning paradigm
মৌলিক উৎস	Amplayo, R. K., & Lapata, M. (2020). Unsupervised Opinion Summarization with Noisy Autoencoder. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 1934–1945.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
অপর নাম	weak supervision summarization, distantly supervised summarization, noisy-label summarization, pseudo-label summarization	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
সম্পর্কিত	1	3
সারসংক্ষেপ	Weakly supervised text summarization trains abstractive or extractive summarization models without manually annotated reference summaries. Instead of costly human labels, it exploits weak signals — heuristic rules, distant supervision, noisy automatic labels, or self-supervised objectives — to guide sequence-to-sequence or transformer models toward producing coherent, concise summaries of input documents.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.