diff --git a/extra/example_data/textcat_example_data/CC_BY-SA-3.0.txt b/extra/example_data/textcat_example_data/CC_BY-SA-3.0.txt index 604209a80..4fcc07c6d 100644 --- a/extra/example_data/textcat_example_data/CC_BY-SA-3.0.txt +++ b/extra/example_data/textcat_example_data/CC_BY-SA-3.0.txt @@ -230,7 +230,7 @@ subject to and limited by the following restrictions: (e.g., "French translation of the Work by Original Author," or "Screenplay based on original Work by Original Author"). The credit required by this Section 4(c) may be implemented in any reasonable - manner; provided, however, that in the case of a Adaptation or + manner; provided, however, that in the case of an Adaptation or Collection, at a minimum such credit will appear, if a credit for all contributing authors of the Adaptation or Collection appears, then as part of these credits and in a manner at least as prominent as the diff --git a/spacy/cli/evaluate.py b/spacy/cli/evaluate.py index 2276ca6b0..7151a884f 100644 --- a/spacy/cli/evaluate.py +++ b/spacy/cli/evaluate.py @@ -38,7 +38,7 @@ def evaluate_cli( predictions. Gold preprocessing helps the annotations align to the tokenization, and may result in sequences of more consistent length. However, it may reduce runtime accuracy due to train/test skew. To render a sample of - dependency parses in a HTML file, set as output directory as the + dependency parses in an HTML file, set as output directory as the displacy_path argument. DOCS: https://spacy.io/api/cli#benchmark-accuracy diff --git a/spacy/matcher/dependencymatcher.pyx b/spacy/matcher/dependencymatcher.pyx index ab5f5d5d1..bfc77878a 100644 --- a/spacy/matcher/dependencymatcher.pyx +++ b/spacy/matcher/dependencymatcher.pyx @@ -377,7 +377,7 @@ cdef class DependencyMatcher: def _resolve_node_operator(self, cache, doc, node, operator): """ - Given a doc, a node (as a index in the doc) and a REL_OP operator + Given a doc, a node (as an index in the doc) and a REL_OP operator returns the list of nodes from the doc that belong to node+operator. """ key = (node, operator) diff --git a/spacy/ml/models/tok2vec.py b/spacy/ml/models/tok2vec.py index b2b803b6e..c6203b066 100644 --- a/spacy/ml/models/tok2vec.py +++ b/spacy/ml/models/tok2vec.py @@ -216,7 +216,7 @@ def CharacterEmbed( ensures that the final character is always in the last position, instead of being in an arbitrary position depending on the word length. - The characters are embedded in a embedding table with a given number of rows, + The characters are embedded in an embedding table with a given number of rows, and the vectors concatenated. A hash-embedded vector of the LOWER of the word is also concatenated on, and the result is then passed through a feed-forward network to construct a single vector to represent the information. diff --git a/website/docs/api/architectures.mdx b/website/docs/api/architectures.mdx index 956234ac0..67d6435b1 100644 --- a/website/docs/api/architectures.mdx +++ b/website/docs/api/architectures.mdx @@ -194,7 +194,7 @@ characters would be `"jumpping"`: 4 from the start, 4 from the end. This ensures that the final character is always in the last position, instead of being in an arbitrary position depending on the word length. -The characters are embedded in a embedding table with a given number of rows, +The characters are embedded in an embedding table with a given number of rows, and the vectors concatenated. A hash-embedded vector of the `NORM` of the word is also concatenated on, and the result is then passed through a feed-forward network to construct a single vector to represent the information. @@ -599,7 +599,7 @@ Construct a RoBERTa transformer model. ### spacy-curated-transformers.XlmrTransformer.v1 -Construct a XLM-RoBERTa transformer model. +Construct an XLM-RoBERTa transformer model. | Name | Description | | ------------------------------ | ---------------------------------------------------------------------------------------- | diff --git a/website/docs/api/cli.mdx b/website/docs/api/cli.mdx index add6b1446..92786b7cb 100644 --- a/website/docs/api/cli.mdx +++ b/website/docs/api/cli.mdx @@ -1238,7 +1238,7 @@ Evaluate the accuracy of a trained pipeline. Expects a loadable spaCy pipeline sentences and tokens for the predictions. Gold preprocessing helps the annotations align to the tokenization, and may result in sequences of more consistent length. However, it may reduce runtime accuracy due to train/test -skew. To render a sample of dependency parses in a HTML file using the +skew. To render a sample of dependency parses in an HTML file using the [displaCy visualizations](/usage/visualizers), set as output directory as the `--displacy-path` argument. diff --git a/website/docs/api/curatedtransformer.mdx b/website/docs/api/curatedtransformer.mdx index 3e63ef7c2..98e65b05d 100644 --- a/website/docs/api/curatedtransformer.mdx +++ b/website/docs/api/curatedtransformer.mdx @@ -537,7 +537,7 @@ Construct a callback that initializes a character piece encoder model. | ----------- | --------------------------------------------------------------------------- | | `path` | Path to the serialized character model. ~~Path~~ | | `bos_piece` | Piece used as a beginning-of-sentence token. Defaults to `"[BOS]"`. ~~str~~ | -| `eos_piece` | Piece used as a end-of-sentence token. Defaults to `"[EOS]"`. ~~str~~ | +| `eos_piece` | Piece used as an end-of-sentence token. Defaults to `"[EOS]"`. ~~str~~ | | `unk_piece` | Piece used as a stand-in for unknown tokens. Defaults to `"[UNK]"`. ~~str~~ | | `normalize` | Unicode normalization form to use. Defaults to `"NFKC"`. ~~str~~ | diff --git a/website/docs/api/spancategorizer.mdx b/website/docs/api/spancategorizer.mdx index 98a1948ee..3da3d1785 100644 --- a/website/docs/api/spancategorizer.mdx +++ b/website/docs/api/spancategorizer.mdx @@ -80,7 +80,7 @@ architectures and their arguments and hyperparameters. | Setting | Description | | --------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `suggester` | A function that [suggests spans](#suggesters). Spans are returned as a ragged array with two integer columns, for the start and end positions. Defaults to [`ngram_suggester`](#ngram_suggester). ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ | -| `model` | A model instance that is given a a list of documents and `(start, end)` indices representing candidate span offsets. The model predicts a probability for each category for each span. Defaults to [SpanCategorizer](/api/architectures#SpanCategorizer). ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ | +| `model` | A model instance that is given a list of documents and `(start, end)` indices representing candidate span offsets. The model predicts a probability for each category for each span. Defaults to [SpanCategorizer](/api/architectures#SpanCategorizer). ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ | | `spans_key` | Key of the [`Doc.spans`](/api/doc#spans) dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. Defaults to `"sc"`. ~~str~~ | | `threshold` | Minimum probability to consider a prediction positive. Spans with a positive prediction will be saved on the Doc. Meant to be used in combination with the multi-class `spancat` component with a `Logistic` scoring layer. Defaults to `0.5`. ~~float~~ | | `max_positive` | Maximum number of labels to consider positive per span. Defaults to `None`, indicating no limit. Meant to be used together with the `spancat` component and defaults to 0 with `spancat_singlelabel`. ~~Optional[int]~~ | @@ -133,7 +133,7 @@ shortcut for this and instantiate the component using its string name and | Name | Description | | --------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `vocab` | The shared vocabulary. ~~Vocab~~ | -| `model` | A model instance that is given a a list of documents and `(start, end)` indices representing candidate span offsets. The model predicts a probability for each category for each span. ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ | +| `model` | A model instance that is given a list of documents and `(start, end)` indices representing candidate span offsets. The model predicts a probability for each category for each span. ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ | | `suggester` | A function that [suggests spans](#suggesters). Spans are returned as a ragged array with two integer columns, for the start and end positions. ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ | | `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ | | _keyword-only_ | | diff --git a/website/docs/usage/v2-1.mdx b/website/docs/usage/v2-1.mdx index 261525d0f..3dca211f4 100644 --- a/website/docs/usage/v2-1.mdx +++ b/website/docs/usage/v2-1.mdx @@ -294,7 +294,7 @@ if all of your models are up to date, you can run the ``` - The [`spacy init-model`](/api/cli#init-model) command now uses a `--jsonl-loc` - argument to pass in a a newline-delimited JSON (JSONL) file containing one + argument to pass in a newline-delimited JSON (JSONL) file containing one lexical entry per line instead of a separate `--freqs-loc` and `--clusters-loc`. diff --git a/website/meta/universe.json b/website/meta/universe.json index 1f55d9616..dc65730a3 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1192,7 +1192,7 @@ "tags": [ "AWS" ], - "slogan": "spaCy as a AWS Lambda Layer", + "slogan": "spaCy as an AWS Lambda Layer", "description": "A collection of Python Packages as AWS Lambda(λ) Layers", "github": "keithrozario/Klayers", "pip": "", @@ -3647,7 +3647,7 @@ "id": "spacysetfit", "title": "spaCy-SetFit", "slogan": "An an easy and intuitive approach to use SetFit in combination with spaCy.", - "description": "spaCy-SetFit is a Python library that extends spaCy's text categorization capabilities by incorporating SetFit for few-shot classification. It allows you to train a text categorizer using a intuitive dictionary. \n\nThe library integrates with spaCy's pipeline architecture, enabling easy integration and configuration of the text categorizer component. You can provide a training dataset containing inlier and outlier examples, and spaCy-SetFit will use the paraphrase-MiniLM-L3-v2 model for training the text categorizer with SetFit. Once trained, you can use the categorizer to classify new text and obtain category probabilities.", + "description": "spaCy-SetFit is a Python library that extends spaCy's text categorization capabilities by incorporating SetFit for few-shot classification. It allows you to train a text categorizer using an intuitive dictionary. \n\nThe library integrates with spaCy's pipeline architecture, enabling easy integration and configuration of the text categorizer component. You can provide a training dataset containing inlier and outlier examples, and spaCy-SetFit will use the paraphrase-MiniLM-L3-v2 model for training the text categorizer with SetFit. Once trained, you can use the categorizer to classify new text and obtain category probabilities.", "github": "davidberenstein1957/spacy-setfit", "pip": "spacy-setfit", "thumb": "https://raw.githubusercontent.com/davidberenstein1957/spacy-setfit/main/logo.png",