Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by _inesmontani on 2019-07-17 (UTC).

Here's the built-in spaCy version for aligning different tokenization (e.g. 🤗's BERT tokens and spaCy tokens):

```
from https://t.co/rsigVJnBju import align

cost, a2b, b2a, a2b_multi, b2a_multi = align(bert_tokens, spacy_tokens)
``` pic.twitter.com/tICtGXNSem

— Ines Montani 〰️ (@_inesmontani) July 17, 2019
nlptool
by _inesmontani on 2019-07-17 (UTC).

📖 Also just added usage and API docs for tokenization alignment, including an example of how to interpret the generated alignment information: https://t.co/00puBek3df pic.twitter.com/fLgYV1rEDj

— Ines Montani 〰️ (@_inesmontani) July 17, 2019
nlptool
by revodavid on 2019-07-17 (UTC).

Microsoft open-sources scripts and notebooks to pre-train and finetune BERT natural language model with domain-specific texts: https://t.co/JRe0e6joP2

— David Smith (@revodavid) July 17, 2019
nlptoolw_code

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib