Skip to content

Commit

Permalink
Add TextCatReduce.v1 (explosion#13181)
Browse files Browse the repository at this point in the history 
* Add TextCatReduce.v1

This is a textcat classifier that pools the vectors generated by a
tok2vec implementation and then applies a classifier to the pooled
representation. Three reductions are supported for pooling: first, max,
and mean. When multiple reductions are enabled, the reductions are
concatenated before providing them to the classification layer.

This model is a generalization of the TextCatCNN model, which only
supports mean reductions and is a bit of a misnomer, because it can also
be used with transformers. This change also reimplements TextCatCNN.v2
using the new TextCatReduce.v1 layer.

* Doc fixes

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Fully specify `TextCatCNN` <-> `TextCatReduce` equivalence

* Move TextCatCNN docs to legacy, in prep for moving to spacy-legacy

* Add back a test for TextCatCNN.v2

* Replace TextCatCNN in pipe configurations and templates

* Add an infobox to the `TextCatReduce` section with an `TextCatCNN` anchor

* Add last reduction (`use_reduce_last`)

* Remove non-working TextCatCNN Netlify redirect

* Revert layer changes for the quickstart

* Revert one more quickstart change

* Remove unused import

* Fix docstring

* Fix setting name in error message

---------

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
  • Loading branch information
@danieldk @adrianeboyd @jikanter
3 people authored and jikanter committed May 21, 2024
1 parent 3c76d52 commit a96dfbf
Show file tree
Hide file tree
Showing 3 changed files with 7 additions and 85 deletions.
3 changes: 3 additions & 0 deletions spacy/errors.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -976,6 +976,9 @@ class Errors(metaclass=ErrorsWithCodes):
E1055 = ("The 'replace_listener' callback expects {num_params} parameters, "
"but only callbacks with one or three parameters are supported")
E1056 = ("The `TextCatBOW` architecture expects a length of at least 1, was {length}.")
E1057 = ("The `TextCatReduce` architecture must be used with at least one "
"reduction. Please enable one of `use_reduce_first`, "
"`use_reduce_last`, `use_reduce_max` or `use_reduce_mean`.")

# v4 error strings
E4000 = ("Expected a Doc as input, but got: '{type}'")
Expand Down
11 changes: 4 additions & 7 deletions spacy/tests/pipeline/test_textcat.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -502,9 +502,9 @@ def test_resize(name, textcat_config):
("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
# CNN
("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
# REDUCE
("textcat", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
("textcat_multilabel", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
],
)
# fmt: on
Expand Down Expand Up @@ -752,12 +752,9 @@ def test_overfitting_IO_multi():
# ENSEMBLE V2
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
# CNN V2
# CNN V2 (legacy)
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
# PARAMETRIC ATTENTION V1
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatParametricAttention.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatParametricAttention.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
# REDUCE V1
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
Expand Down
78 changes: 0 additions & 78 deletions website/docs/api/architectures.mdx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1020,46 +1020,6 @@ but used an internal `tok2vec` instead of taking it as argument:
### spacy.TextCatBOW.v3 {id="TextCatBOW"}
> #### Example Config
>
> ```ini
> [model]
> @architectures = "spacy.TextCatCNN.v2"
> exclusive_classes = false
> nO = null
>
> [model.tok2vec]
> @architectures = "spacy.HashEmbedCNN.v2"
> pretrained_vectors = null
> width = 96
> depth = 4
> embed_size = 2000
> window_size = 1
> maxout_pieces = 3
> subword_features = true
> ```
A neural network model where token vectors are calculated using a CNN. The
vectors are mean pooled and used as features in a feed-forward network. This
architecture is usually less accurate than the ensemble, but runs faster.
| Name | Description |
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ |
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
<Accordion title="spacy.TextCatCNN.v1 definition" spaced>
[TextCatCNN.v1](/api/legacy#TextCatCNN_v1) had the exact same signature, but was
not yet resizable. Since v2, new labels can be added to this component, even
after training.
</Accordion>
### spacy.TextCatBOW.v3 {id="TextCatBOW"}
> #### Example Config
>
> ```ini
Expand Down Expand Up @@ -1096,44 +1056,6 @@ the others, but may not be as accurate, especially if texts are short.
</Accordion>
### spacy.TextCatParametricAttention.v1 {id="TextCatParametricAttention"}
> #### Example Config
>
> ```ini
> [model]
> @architectures = "spacy.TextCatParametricAttention.v1"
> exclusive_classes = true
> nO = null
>
> [model.tok2vec]
> @architectures = "spacy.Tok2Vec.v2"
>
> [model.tok2vec.embed]
> @architectures = "spacy.MultiHashEmbed.v2"
> width = 64
> rows = [2000, 2000, 1000, 1000, 1000, 1000]
> attrs = ["ORTH", "LOWER", "PREFIX", "SUFFIX", "SHAPE", "ID"]
> include_static_vectors = false
>
> [model.tok2vec.encode]
> @architectures = "spacy.MaxoutWindowEncoder.v2"
> width = ${model.tok2vec.embed.width}
> window_size = 1
> maxout_pieces = 3
> depth = 2
> ```
A neural network model that is built upon Tok2Vec and uses parametric attention
to attend to tokens that are relevant to text classification.
| Name | Description |
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `tok2vec` | The `tok2vec` layer to build the neural network upon. ~~Model[List[Doc], List[Floats2d]]~~ |
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
### spacy.TextCatReduce.v1 {id="TextCatReduce"}
> #### Example Config
Expand Down

0 comments on commit a96dfbf

Please sign in to comment.