https://research.google/pubs/charformer-fast-character-transformers-via-gradient-based-subword-tokenization/
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization
fastcharactertransformersviagradient
https://www.tensorflow.org/text/guide/subwords_tokenizer?authuser=3
Subword tokenizers | Text | TensorFlow
subwordtokenizerstexttensorflow
https://arxiv.org/abs/2309.03180
[2309.03180] Arithmetical subword complexity of automatic sequences
Abstract page for arXiv paper 2309.03180: Arithmetical subword complexity of automatic sequences
230903180subwordcomplexityautomatic
https://aclanthology.org/2026.vardial-1.9/
A Subword Embedding Approach for Variation Detection in Luxembourgish User Comments - ACL Anthology
Anne-Marie Lutgen, Alistair Plum, Christoph Purschke. Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects. 2026.
https://www.tensorflow.org/text/guide/subwords_tokenizer?authuser=1
Subword tokenizers | Text | TensorFlow
subwordtokenizerstexttensorflow
https://openreview.net/forum?id=JcfISE1-u4
WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual...
Recently, large pretrained language models (LMs) have gained popularity. Training these models requires ever more computational resources and most of the...
wechseleffectiveinitializationsubword
https://www.amazon.science/publications/swan-subword-alignment-network-for-hmm-free-word-timing-estimation-in-end-to-end-automatic-speech-recognition
SWAN: SubWord Alignment Network for HMM-free word timing estimation in end-to-end automatic speech...
End-to-end (E2E) automatic speech recognition (ASR) systems often exploited pre-trained hidden Markov model (HMM) systems for word timing estimation (WTE), due...
https://www.tensorflow.org/text/guide/subwords_tokenizer?authuser=19
Subword tokenizers | Text | TensorFlow
subwordtokenizerstexttensorflow