diff --git a/spacy/tests/README.md b/spacy/tests/README.md index 833dc9266..82fabcc77 100644 --- a/spacy/tests/README.md +++ b/spacy/tests/README.md @@ -109,12 +109,12 @@ Loading the models is expensive and not necessary if you're not actually testing ```python def test_doc_token_api_strings(en_vocab): - text = "Give it back! He pleaded." + words = ["Give", "it", "back", "!", "He", "pleaded", "."] pos = ['VERB', 'PRON', 'PART', 'PUNCT', 'PRON', 'VERB', 'PUNCT'] heads = [0, 0, 0, 0, 5, 5, 5] deps = ['ROOT', 'dobj', 'prt', 'punct', 'nsubj', 'ROOT', 'punct'] - doc = Doc(en_vocab, [t.text for t in tokens], pos=pos, heads=heads, deps=deps) + doc = Doc(en_vocab, words=words, pos=pos, heads=heads, deps=deps) assert doc[0].text == 'Give' assert doc[0].lower_ == 'give' assert doc[0].pos_ == 'VERB' diff --git a/website/docs/api/language.md b/website/docs/api/language.md index 51e9a5e10..b2a5a776e 100644 --- a/website/docs/api/language.md +++ b/website/docs/api/language.md @@ -786,15 +786,13 @@ doesn't, the pipeline analysis won't catch that. ### Pretty ============================= Pipeline Overview ============================= -# Component Assigns Requires Scores Retokenizes -- ------------- --------------- -------------- --------- ----------- -0 tagger token.tag tag_acc False - pos_acc - lemma_acc +# Component Assigns Requires Scores Retokenizes +- ------------- --------------- -------------- ----------- ----------- +0 tagger token.tag tag_acc False -1 entity_linker token.ent_kb_id doc.ents False - doc.sents - token.ent_iob +1 entity_linker token.ent_kb_id doc.ents nel_micro_f False + doc.sents nel_micro_r + token.ent_iob nel_micro_p token.ent_type diff --git a/website/docs/usage/linguistic-features.md b/website/docs/usage/linguistic-features.md index af07a438f..9a2b538d1 100644 --- a/website/docs/usage/linguistic-features.md +++ b/website/docs/usage/linguistic-features.md @@ -54,9 +54,9 @@ create a surface form. Here are some examples: | I don't watch the news, I read the paper | read | read | `VERB` | `VerbForm=Fin`, `Mood=Ind`, `Tense=Pres` | | I read the paper yesterday | read | read | `VERB` | `VerbForm=Fin`, `Mood=Ind`, `Tense=Past` | -Morphological features are stored in the [`MorphAnalysis`](/api/morphanalysis) -under `Token.morph`, which allows you to access individual morphological -features. +Morphological features are stored in the +[`MorphAnalysis`](/api/morphology#morphanalysis) under `Token.morph`, which +allows you to access individual morphological features. > #### 📝 Things to try > diff --git a/website/docs/usage/processing-pipelines.md b/website/docs/usage/processing-pipelines.md index ef44009ae..e55fc9ebd 100644 --- a/website/docs/usage/processing-pipelines.md +++ b/website/docs/usage/processing-pipelines.md @@ -487,15 +487,13 @@ analysis = nlp.analyze_pipes(pretty=True) ### Pretty ============================= Pipeline Overview ============================= -# Component Assigns Requires Scores Retokenizes -- ------------- --------------- -------------- --------- ----------- -0 tagger token.tag tag_acc False - pos_acc - lemma_acc +# Component Assigns Requires Scores Retokenizes +- ------------- --------------- -------------- ----------- ----------- +0 tagger token.tag tag_acc False -1 entity_linker token.ent_kb_id doc.ents False - doc.sents - token.ent_iob +1 entity_linker token.ent_kb_id doc.ents nel_micro_f False + doc.sents nel_micro_r + token.ent_iob nel_micro_p token.ent_type