spaCy/website/meta/sidebars.json

167 lines
7.7 KiB
JSON
Raw Normal View History

[
{
"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" },
2021-06-22 08:23:18 +03:00
{ "text": "New in v3.0", "url": "/usage/v3" },
{ "text": "New in v3.1", "url": "/usage/v3-1" },
{ "text": "New in v3.2", "url": "/usage/v3-2" },
{ "text": "New in v3.3", "url": "/usage/v3-3" },
{ "text": "New in v3.4", "url": "/usage/v3-4" },
{ "text": "New in v3.5", "url": "/usage/v3-5" },
{ "text": "New in v3.6", "url": "/usage/v3-6" }
]
},
{
"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" },
2020-08-18 01:49:19 +03:00
{
"text": "Embeddings & Transformers",
"url": "/usage/embeddings-transformers"
},
{
"text": "Large Language Models",
"url": "/usage/large-language-models",
2020-08-18 01:49:19 +03:00
"tag": "new"
},
{ "text": "Training Models", "url": "/usage/training" },
2020-08-21 17:11:38 +03:00
{
"text": "Layers & Model Architectures",
"url": "/usage/layers-architectures"
2020-08-21 17:11:38 +03:00
},
{ "text": "spaCy Projects", "url": "/usage/projects" },
{ "text": "Saving & Loading", "url": "/usage/saving-loading" },
{ "text": "Visualizers", "url": "/usage/visualizers" }
]
},
{
2020-07-05 17:11:16 +03:00
"label": "Resources",
"items": [
{ "text": "Project Templates", "url": "https://github.com/explosion/projects" },
2022-02-08 13:46:42 +03:00
{ "text": "v2.x Documentation", "url": "https://v2.spacy.io" },
{
"text": "Custom Solutions",
"url": "https://explosion.ai/custom-solutions"
2022-02-08 13:46:42 +03:00
}
2020-07-05 17:11:16 +03:00
]
}
]
},
{
"section": "models",
"items": [
{
"label": "Models",
"items": [{ "text": "Overview", "url": "/models" }]
},
{
"label": "Trained Pipelines",
"items": []
}
]
},
{
"section": "api",
"items": [
{
"label": "Overview",
"items": [
2020-07-03 17:48:21 +03:00
{ "text": "Library Architecture", "url": "/api" },
{ "text": "Model Architectures", "url": "/api/architectures" },
2020-07-05 17:11:16 +03:00
{ "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" },
2020-09-21 14:46:21 +03:00
{ "text": "DocBin", "url": "/api/docbin" },
2020-07-04 15:23:10 +03:00
{ "text": "Example", "url": "/api/example" },
2020-09-21 14:46:21 +03:00
{ "text": "Language", "url": "/api/language" },
{ "text": "Lexeme", "url": "/api/lexeme" },
{ "text": "Span", "url": "/api/span" },
{ "text": "SpanGroup", "url": "/api/spangroup" },
2020-09-21 14:46:21 +03:00
{ "text": "Token", "url": "/api/token" }
]
},
{
"label": "Pipeline",
"items": [
{ "text": "AttributeRuler", "url": "/api/attributeruler" },
{ "text": "CoreferenceResolver", "url": "/api/coref" },
Documentation for spacy-curated-transformers (#12677) * initial * initial documentation run * fix typo * Remove mentions of Torchscript and quantization Both are disabled in the initial release of `spacy-curated-transformers`. * Fix `piece_encoder` entries * Remove `spacy-transformers`-specific warning * Fix duplicate entries in tables * Doc fixes Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Remove type aliases * Fix copy-paste typo * Change `debug pieces` version tag to `3.7` * Set curated transformers API version to `3.7` * Fix transformer listener naming * Add docs for `init fill-config-transformer` * Update CLI command invocation syntax * Update intro section of the pipeline component docs * Fix source URL * Add a note to the architectures section about the `init fill-config-transformer` CLI command * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update CLI command name, args * Remove hyphen from the `curated-transformers.mdx` filename * Fix links * Remove placeholder text * Add text to the model/tokenizer loader sections * Fill in the `DocTransformerOutput` section * Formatting fixes * Add curated transformer page to API docs sidebar * More formatting fixes * Remove TODO comment * Remove outdated info about default config * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Add link to HF model hub * `prettier` --------- Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2023-08-29 18:52:16 +03:00
{ "text": "CuratedTransformer", "url": "/api/curatedtransformer" },
{ "text": "DependencyParser", "url": "/api/dependencyparser" },
{ "text": "EditTreeLemmatizer", "url": "/api/edittreelemmatizer" },
2020-09-21 14:46:21 +03:00
{ "text": "EntityLinker", "url": "/api/entitylinker" },
{ "text": "EntityRecognizer", "url": "/api/entityrecognizer" },
{ "text": "EntityRuler", "url": "/api/entityruler" },
{ "text": "Large Language Models", "url": "/api/large-language-models" },
2020-09-21 14:46:21 +03:00
{ "text": "Lemmatizer", "url": "/api/lemmatizer" },
{ "text": "Morphologizer", "url": "/api/morphologizer" },
2020-07-04 15:23:10 +03:00
{ "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" },
2020-09-21 14:46:21 +03:00
{ "text": "Sentencizer", "url": "/api/sentencizer" },
Add SpanCategorizer component (#6747) * 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>
2021-06-24 13:35:27 +03:00
{ "text": "SpanCategorizer", "url": "/api/spancategorizer" },
SpanFinder into spaCy from experimental (#12507) * span finder integrated into spacy from experimental * black * isort * black * default spankey constant * black * Update spacy/pipeline/spancat.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * rename * rename * max_length and min_length as Optional[int] and strict checking * black * mypy fix for integer type infinity * revert line order * implement all comparison operators for inf int * avoid two for loops over all docs by not precomputing * interleave thresholding with span creation * black * revert to not interleaving (relized its faster) * black * Update spacy/errors.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * update dosctring * enforce that the gold and predicted documents have the same text * new error for ensuring reference and predicted texts are the same * remove todo * adjust test * black * handle misaligned tokenization * return correct variable * failing overfit test * only use a single spans_key like in spancat * black * remove debug lines * typo * remove comment * remove near duplicate reduntant method * use the 'spans_key' variable name everywhere * Update spacy/pipeline/span_finder.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * flaky test fix suggestion, hand set bias terms * only test suggester and test result exhaustively * make it clear that the span_finder_suggester is more general (not specific to span_finder) * Update spacy/tests/pipeline/test_span_finder.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Apply suggestions from code review * remove question comment * move preset_spans_suggester test to spancat tests * Add docs and unify default configs for spancat and span finder * Add `allow_overlap=True` to span finder scorer * Fix offset bug in set_annotations * Ignore labels in span finder scorer * Format * Add span_finder to quickstart template * Move settings to self.cfg, store min/max unset as None * Remove debugging * Update docstrings and docs * Update spacy/pipeline/span_finder.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix imports --------- Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2023-06-07 16:52:28 +03:00
{ "text": "SpanFinder", "url": "/api/spanfinder" },
{ "text": "SpanResolver", "url": "/api/span-resolver" },
Add SpanRuler component (#9880) * Add SpanRuler component Add a `SpanRuler` component similar to `EntityRuler` that saves a list of matched spans to `Doc.spans[spans_key]`. The matches from the token and phrase matchers are deduplicated and sorted before assignment but are not otherwise filtered. * Update spacy/pipeline/span_ruler.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix cast * Add self.key property * Use number of patterns as length * Remove patterns kwarg from init * Update spacy/tests/pipeline/test_span_ruler.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Add options for spans filter and setting to ents * Add `spans_filter` option as a registered function' * Make `spans_key` optional and if `None`, set to `doc.ents` instead of `doc.spans[spans_key]`. * Update and generalize tests * Add test for setting doc.ents, fix key property type * Fix typing * Allow independent doc.spans and doc.ents * If `spans_key` is set, set `doc.spans` with `spans_filter`. * If `annotate_ents` is set, set `doc.ents` with `ents_fitler`. * Use `util.filter_spans` by default as `ents_filter`. * Use a custom warning if the filter does not work for `doc.ents`. * Enable use of SpanC.id in Span * Support id in SpanRuler as Span.id * Update types * `id` can only be provided as string (already by `PatternType` definition) * Update all uses of Span.id/ent_id in Doc * Rename Span id kwarg to span_id * Update types and docs * Add ents filter to mimic EntityRuler overwrite_ents * Refactor `ents_filter` to take `entities, spans` args for more filtering options * Give registered filters more descriptive names * Allow registered `filter_spans` filter (`spacy.first_longest_spans_filter.v1`) to take any number of `Iterable[Span]` objects as args so it can be used for spans filter or ents filter * Implement future entity ruler as span ruler Implement a compatible `entity_ruler` as `future_entity_ruler` using `SpanRuler` as the underlying component: * Add `sort_key` and `sort_reverse` to allow the sorting behavior to be customized. (Necessary for the same sorting/filtering as in `EntityRuler`.) * Implement `overwrite_overlapping_ents_filter` and `preserve_existing_ents_filter` to support `EntityRuler.overwrite_ents` settings. * Add `remove_by_id` to support `EntityRuler.remove` functionality. * Refactor `entity_ruler` tests to parametrize all tests to test both `entity_ruler` and `future_entity_ruler` * Implement `SpanRuler.token_patterns` and `SpanRuler.phrase_patterns` properties. Additional changes: * Move all config settings to top-level attributes to avoid duplicating settings in the config vs. `span_ruler/cfg`. (Also avoids a lot of casting.) * Format * Fix filter make method name * Refactor to use same error for removing by label or ID * Also provide existing spans to spans filter * Support ids property * Remove token_patterns and phrase_patterns * Update docstrings * Add span ruler docs * Fix types * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Move sorting into filters * Check for all tokens in seen tokens in entity ruler filters * Remove registered sort key * Set Token.ent_id in a backwards-compatible way in Doc.set_ents * Remove sort options from API docs * Update docstrings * Rename entity ruler filters * Fix and parameterize scoring * Add id to Span API docs * Fix typo in API docs * Include explicit labeled=True for scorer Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2022-06-02 14:12:53 +03:00
{ "text": "SpanRuler", "url": "/api/spanruler" },
2020-09-21 14:46:21 +03:00
{ "text": "Tagger", "url": "/api/tagger" },
{ "text": "TextCategorizer", "url": "/api/textcategorizer" },
{ "text": "Tok2Vec", "url": "/api/tok2vec" },
{ "text": "Tokenizer", "url": "/api/tokenizer" },
2020-10-09 11:36:06 +03:00
{ "text": "TrainablePipe", "url": "/api/pipe" },
2020-09-21 14:46:21 +03:00
{ "text": "Transformer", "url": "/api/transformer" },
{ "text": "Other Functions", "url": "/api/pipeline-functions" }
]
},
{
"label": "Matchers",
"items": [
2020-09-21 14:46:21 +03:00
{ "text": "DependencyMatcher", "url": "/api/dependencymatcher" },
{ "text": "Matcher", "url": "/api/matcher" },
2020-09-21 14:46:21 +03:00
{ "text": "PhraseMatcher", "url": "/api/phrasematcher" }
]
},
{
"label": "Other",
"items": [
{ "text": "Attributes", "url": "/api/attributes" },
{ "text": "BaseVectors", "url": "/api/basevectors" },
2020-09-21 14:46:21 +03:00
{ "text": "Corpus", "url": "/api/corpus" },
{ "text": "InMemoryLookupKB", "url": "/api/inmemorylookupkb" },
2020-09-21 14:46:21 +03:00
{ "text": "KnowledgeBase", "url": "/api/kb" },
2019-09-12 15:00:14 +03:00
{ "text": "Lookups", "url": "/api/lookups" },
2020-09-22 10:36:37 +03:00
{ "text": "MorphAnalysis", "url": "/api/morphology#morphanalysis" },
{ "text": "Morphology", "url": "/api/morphology" },
2019-09-18 21:23:21 +03:00
{ "text": "Scorer", "url": "/api/scorer" },
2020-09-21 14:46:21 +03:00
{ "text": "StringStore", "url": "/api/stringstore" },
{ "text": "Vectors", "url": "/api/vectors" },
{ "text": "Vocab", "url": "/api/vocab" }
]
},
{
"label": "Cython",
"items": [
{ "text": "Architecture", "url": "/api/cython" },
2020-09-21 14:46:21 +03:00
{ "text": "Classes", "url": "/api/cython-classes" },
{ "text": "Structs", "url": "/api/cython-structs" }
]
},
{
"label": "Legacy",
2021-06-22 08:23:18 +03:00
"items": [{ "text": "Legacy functions", "url": "/api/legacy" }]
}
]
}
]