Jungmin Yun, Mihyeon Kim, Youngbin Kim. Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 13617-13628, Association for Computational Linguistics, 2023. [doi]
Abstract is missing.