Klaudia Balazy, Mohammadreza Banaei, Rémi Lebret, Jacek Tabor, Karl Aberer. Direction is what you need: Improving Word Embedding Compression in Large Language Models. In Anna Rogers, Iacer Calixto, Ivan Vulic, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz, editors, Proceedings of the 6th Workshop on Representation Learning for NLP, RepL4NLP@ACL-IJCNLP 2021, Online, August 6, 2021. pages 322-330, Association for Computational Linguistics, 2021. [doi]
Abstract is missing.