* Use cosine loss in Cloze multitask
* Fix char_embed for gpu
* Call resume_training for base model in train CLI
* Fix bilstm_depth default in pretrain command
* Implement character-based pretraining objective
* Use chars loss in ClozeMultitask
* Add method to decode predicted characters
* Fix number characters
* Rescale gradients for mlm
* Fix char embed+vectors in ml
* Fix pipes
* Fix pretrain args
* Move get_characters_loss
* Fix import
* Fix import
* Mention characters loss option in pretrain
* Remove broken 'self attention' option in pretrain
* Revert "Remove broken 'self attention' option in pretrain"
This reverts commit 56b820f6af.
* Document 'characters' objective of pretrain
Very minor fix in docs, specifically in this part:
```
matcher = PhraseMatcher(nlp.vocab)
> for doc in matcher.pipe(texts, batch_size=50):
> pass
```
`texts` suggests the input is an iterable of strings. I replaced it for `docs`.
* Update website models for v2.3.0
* Add docs for Chinese word segmentation
* Tighten up Chinese docs section
* Merge branch 'master' into docs/v2.3.0 [ci skip]
* Merge branch 'master' into docs/v2.3.0 [ci skip]
* Auto-format and update version
* Update matcher.md
* Update languages and sorting
* Typo in landing page
* Infobox about token_match behavior
* Add meta and basic docs for Japanese
* POS -> TAG in models table
* Add info about lookups for normalization
* Updates to API docs for v2.3
* Update adding norm exceptions for adding languages
* Add --omit-extra-lookups to CLI API docs
* Add initial draft of "What's New in v2.3"
* Add new in v2.3 tags to Chinese and Japanese sections
* Add tokenizer to migration section
* Add new in v2.3 flags to init-model
* Typo
* More what's new in v2.3
Co-authored-by: Ines Montani <ines@ines.io>
* added contextualSpellCheck in spacy universe meta
* removed extra formatting by code
* updated with permanent links
* run json linter used by spacy
* filled SCA
* updated the description
To fix the slow tokenizer URL (#4374) and allow `token_match` to take
priority over prefixes and suffixes by default, introduce a new
tokenizer option for a token match pattern that's applied after prefixes
and suffixes but before infixes.
* `debug-data`: determine coverage of provided vectors
* `evaluate`: support `blank:lg` model to make it possible to just evaluate
tokenization
* `init-model`: add option to truncate vectors to N most frequent vectors
from word2vec file
* `train`:
* if training on GPU, only run evaluation/timing on CPU in the first
iteration
* if training is aborted, exit with a non-0 exit status
