Matthew Honnibal 3e78e82a83 Experimental character-based pretraining (#5700) ... * 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		2020-07-05 15:48:39 +02:00
..
annotation.md	Update tag maps and docs for English and German (#4501)	2019-10-24 12:56:05 +02:00
cli.md	Experimental character-based pretraining (#5700)	2020-07-05 15:48:39 +02:00
cython-classes.md	Remove u-strings and fix formatting [ci skip]	2019-09-12 16:11:15 +02:00
cython-structs.md	Documentation updates for v2.3.0 (#5593)	2020-06-16 15:37:35 +02:00
cython.md	💫 Update website (#3285)	2019-02-17 19:31:19 +01:00
dependencyparser.md	Remove u-strings and fix formatting [ci skip]	2019-09-12 16:11:15 +02:00
doc.md	Remove references to textcat spans (#5360)	2020-04-27 18:01:12 +02:00
docbin.md	Fix DocBin.merge() example (#4599)	2019-11-07 11:26:48 +01:00
entitylinker.md	Fix typos and formatting [ci skip]	2019-10-01 12:30:04 +02:00
entityrecognizer.md	update docs for EntityRecognizer.predict	2020-03-28 18:13:02 +01:00
entityruler.md	Describing priority rules for overlapping matches (#5197)	2020-03-26 13:13:22 +01:00
goldcorpus.md	💫 Update website (#3285)	2019-02-17 19:31:19 +01:00
goldparse.md	Fix typos and auto-format [ci skip]	2020-06-16 16:38:45 +02:00
index.md	💫 Update website (#3285)	2019-02-17 19:31:19 +01:00
kb.md	Use consistent spelling	2019-10-02 10:37:39 +02:00
language.md	Amend documentation to Language.evaluate (#5319)	2020-04-16 20:00:18 +02:00
lemmatizer.md	Misspelling on Lemmatizer Example #4406 (#4449)	2019-10-16 23:23:15 +02:00
lexeme.md	Documentation updates for v2.3.0 (#5593)	2020-06-16 15:37:35 +02:00
lookups.md	Fix typos and formatting [ci skip]	2019-10-01 12:30:04 +02:00
matcher.md	Fix typos and auto-format [ci skip]	2020-06-16 16:38:45 +02:00
phrasematcher.md	Fix in docs: pipe(docs) instead of pipe(texts) (#5680)	2020-06-30 20:00:50 +02:00
pipeline-functions.md	Remove u-strings and fix formatting [ci skip]	2019-09-12 16:11:15 +02:00
scorer.md	Update scorer.md [ci skip]	2019-11-21 17:02:43 +01:00
sentencizer.md	Documentation updates for v2.3.0 (#5593)	2020-06-16 15:37:35 +02:00
span.md	Fix formatting and update docs for v2.2.4	2020-03-09 11:17:20 +01:00
stringstore.md	Remove u-strings and fix formatting [ci skip]	2019-09-12 16:11:15 +02:00
tagger.md	Remove u-strings and fix formatting [ci skip]	2019-09-12 16:11:15 +02:00
textcategorizer.md	Remove u-strings and fix formatting [ci skip]	2019-09-12 16:11:15 +02:00
token.md	Documentation updates for v2.3.0 (#5593)	2020-06-16 15:37:35 +02:00
tokenizer.md	Rename to url_match	2020-05-22 12:41:03 +02:00
top-level.md	Fix formatting and update docs for v2.2.4	2020-03-09 11:17:20 +01:00
vectors.md	Update nlp.vectors to nlp.vocab.vectors (#5357)	2020-04-27 10:53:05 +02:00
vocab.md	Documentation updates for v2.3.0 (#5593)	2020-06-16 15:37:35 +02:00