UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings

UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings Zhi Li author Yuchen Zhai author Chengyu Wang author Minghui Qiu author Kailiang Li author Yin Zhang author 2021-11 text Findings of the Association for Computational Linguistics: EMNLP 2021 Marie-Francine Moens editor Xuanjing Huang editor Lucia Specia editor Scott Wen-tau Yih editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication li-etal-2021-uncle-explicitly 10.18653/v1/2021.findings-emnlp.156 https://aclanthology.org/2021.findings-emnlp.156/ 2021-11 1815 1828