Pavel Chizhov Catherine Arnett Elizaveta Korotkova Ivan P. Yamshchikov BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training. 16587-16604 2024 EMNLP https://doi.org/10.18653/v1/2024.emnlp-main.925 https://aclanthology.org/2024.emnlp-main.925 conf/emnlp/2024 db/conf/emnlp/emnlp2024.html#ChizhovAKY24