mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
f9946154d9
* Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
146 lines
6.3 KiB
JSON
146 lines
6.3 KiB
JSON
[
|
|
{
|
|
"section": "usage",
|
|
"items": [
|
|
{
|
|
"label": "Get started",
|
|
"items": [
|
|
{ "text": "Installation", "url": "/usage" },
|
|
{ "text": "Models & Languages", "url": "/usage/models" },
|
|
{ "text": "Facts & Figures", "url": "/usage/facts-figures" },
|
|
{ "text": "spaCy 101", "url": "/usage/spacy-101" },
|
|
{ "text": "New in v3.0", "url": "/usage/v3" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Guides",
|
|
"items": [
|
|
{ "text": "Linguistic Features", "url": "/usage/linguistic-features" },
|
|
{ "text": "Rule-based Matching", "url": "/usage/rule-based-matching" },
|
|
{ "text": "Processing Pipelines", "url": "/usage/processing-pipelines" },
|
|
{
|
|
"text": "Embeddings & Transformers",
|
|
"url": "/usage/embeddings-transformers",
|
|
"tag": "new"
|
|
},
|
|
{ "text": "Training Models", "url": "/usage/training", "tag": "new" },
|
|
{
|
|
"text": "Layers & Model Architectures",
|
|
"url": "/usage/layers-architectures",
|
|
"tag": "new"
|
|
},
|
|
{ "text": "spaCy Projects", "url": "/usage/projects", "tag": "new" },
|
|
{ "text": "Saving & Loading", "url": "/usage/saving-loading" },
|
|
{ "text": "Visualizers", "url": "/usage/visualizers" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Resources",
|
|
"items": [
|
|
{ "text": "Project Templates", "url": "https://github.com/explosion/projects" },
|
|
{ "text": "v2.x Documentation", "url": "https://v2.spacy.io" }
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"section": "models",
|
|
"items": [
|
|
{
|
|
"label": "Models",
|
|
"items": [{ "text": "Overview", "url": "/models" }]
|
|
},
|
|
{
|
|
"label": "Trained Pipelines",
|
|
"items": []
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"section": "api",
|
|
"items": [
|
|
{
|
|
"label": "Overview",
|
|
"items": [
|
|
{ "text": "Library Architecture", "url": "/api" },
|
|
{ "text": "Model Architectures", "url": "/api/architectures" },
|
|
{ "text": "Data Formats", "url": "/api/data-formats" },
|
|
{ "text": "Command Line", "url": "/api/cli" },
|
|
{ "text": "Functions", "url": "/api/top-level" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Containers",
|
|
"items": [
|
|
{ "text": "Doc", "url": "/api/doc" },
|
|
{ "text": "DocBin", "url": "/api/docbin" },
|
|
{ "text": "Example", "url": "/api/example" },
|
|
{ "text": "Language", "url": "/api/language" },
|
|
{ "text": "Lexeme", "url": "/api/lexeme" },
|
|
{ "text": "Span", "url": "/api/span" },
|
|
{ "text": "SpanGroup", "url": "/api/spangroup" },
|
|
{ "text": "Token", "url": "/api/token" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Pipeline",
|
|
"items": [
|
|
{ "text": "AttributeRuler", "url": "/api/attributeruler" },
|
|
{ "text": "DependencyParser", "url": "/api/dependencyparser" },
|
|
{ "text": "EntityLinker", "url": "/api/entitylinker" },
|
|
{ "text": "EntityRecognizer", "url": "/api/entityrecognizer" },
|
|
{ "text": "EntityRuler", "url": "/api/entityruler" },
|
|
{ "text": "Lemmatizer", "url": "/api/lemmatizer" },
|
|
{ "text": "Morphologizer", "url": "/api/morphologizer" },
|
|
{ "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" },
|
|
{ "text": "Sentencizer", "url": "/api/sentencizer" },
|
|
{ "text": "SpanCategorizer", "url": "/api/spancategorizer" },
|
|
{ "text": "Tagger", "url": "/api/tagger" },
|
|
{ "text": "TextCategorizer", "url": "/api/textcategorizer" },
|
|
{ "text": "Tok2Vec", "url": "/api/tok2vec" },
|
|
{ "text": "Tokenizer", "url": "/api/tokenizer" },
|
|
{ "text": "TrainablePipe", "url": "/api/pipe" },
|
|
{ "text": "Transformer", "url": "/api/transformer" },
|
|
{ "text": "Other Functions", "url": "/api/pipeline-functions" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Matchers",
|
|
"items": [
|
|
{ "text": "DependencyMatcher", "url": "/api/dependencymatcher" },
|
|
{ "text": "Matcher", "url": "/api/matcher" },
|
|
{ "text": "PhraseMatcher", "url": "/api/phrasematcher" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Other",
|
|
"items": [
|
|
{ "text": "Corpus", "url": "/api/corpus" },
|
|
{ "text": "KnowledgeBase", "url": "/api/kb" },
|
|
{ "text": "Lookups", "url": "/api/lookups" },
|
|
{ "text": "MorphAnalysis", "url": "/api/morphology#morphanalysis" },
|
|
{ "text": "Morphology", "url": "/api/morphology" },
|
|
{ "text": "Scorer", "url": "/api/scorer" },
|
|
{ "text": "StringStore", "url": "/api/stringstore" },
|
|
{ "text": "Vectors", "url": "/api/vectors" },
|
|
{ "text": "Vocab", "url": "/api/vocab" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Cython",
|
|
"items": [
|
|
{ "text": "Architecture", "url": "/api/cython" },
|
|
{ "text": "Classes", "url": "/api/cython-classes" },
|
|
{ "text": "Structs", "url": "/api/cython-structs" }
|
|
]
|
|
},
|
|
{
|
|
"label": "Legacy",
|
|
"items": [
|
|
{ "text": "Legacy functions", "url": "/api/legacy" }
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|