3 papers
cs.CL2024
Distributional Properties of Subword Regularization
Marco Cognetta, Vilém Zouhar, Naoaki Okazaki
Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to…
cs.CL2024
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
Marco Cognetta, Tatsuya Hiraoka, Naoaki Okazaki +2
We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique…
cs.CL2024
Two Counterexamples to Tokenization and the Noiseless Channel
Marco Cognetta, Vilém Zouhar, Sangwhan Moon +1
In Tokenization and the Noiseless Channel (Zouhar et al., 2023a), Rényi efficiency is suggested as an intrinsic mechanism for evaluating a tokenizer: for NLP tasks, the tokenizer w…