Pre-trained language model with feature reduction and no fine-tuning

• 主要な著者: Kit, Y. H., Mokji, M.
• フォーマット: Conference or Workshop Item
• 出版事項: 2022
• 主題: TK Electrical engineering. Electronics Nuclear engineering
• オンライン･アクセス: http://eprints.utm.my/id/eprint/98842/; http://dx.doi.org/10.1007/978-981-19-3923-5_59

Pre-trained language models were proven to achieve excellent results in Natural Language Processing tasks such as Sentiment Analysis. However, the number of sentence embeddings from the base model of Bidirectional Encoder from Transformer (BERT) is 768 for a sentence, and there will be more than mil...