Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES

Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES

Byte-pair encoding and Unigram-LM create distinctly different subword vocabularies in chemical language models, with no convergence between the two approaches across diverse corpus…

Hugging Face · Daily Papers ·Hunter Heidenreich · ·▲ 2 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Hunter Heidenreich

  • 2 upvotes da comunidade
  • Temas: byte-pair encoding, Unigram-LM, SMILES, tokenizer, subword vocabulary, Jaccard overlap

Resumo

Resumo original (em inglês), extraído do paper:

Byte-pair encoding and Unigram-LM create distinctly different subword vocabularies in chemical language models, with no convergence between the two approaches across diverse corpus types and vocabulary sizes.

Onde ler

compartilhar: