state_type and extra_state_tokens instead of nr_feature_tokens

spacy/cli/templates/quickstart_training.jinja

@@ -59,7 +59,8 @@ factory = "parser"
 
 [components.parser.model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 8
+state_type = "deps"
+extra_state_tokens = false
 hidden_width = 128
 maxout_pieces = 3
 use_upper = false
@@ -79,7 +80,8 @@ factory = "ner"
 
 [components.ner.model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 3
+state_type = "ner"
+extra_state_tokens = false
 hidden_width = 64
 maxout_pieces = 2
 use_upper = false
@@ -183,7 +185,8 @@ factory = "parser"
 
 [components.parser.model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 8
+state_type = "deps"
+extra_state_tokens = false
 hidden_width = 128
 maxout_pieces = 3
 use_upper = true
@@ -200,7 +203,8 @@ factory = "ner"
 
 [components.ner.model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 6
+state_type = "ner"
+extra_state_tokens = false
 hidden_width = 64
 maxout_pieces = 2
 use_upper = true

spacy/ml/models/parser.py

@@ -11,7 +11,8 @@ from ...tokens import Doc
 @registry.architectures.register("spacy.TransitionBasedParser.v1")
 def build_tb_parser_model(
     tok2vec: Model[List[Doc], List[Floats2d]],
-    nr_feature_tokens: int,
+    state_type: str,
+    extra_state_tokens: bool,
     hidden_width: int,
     maxout_pieces: int,
     use_upper: bool = True,
@@ -40,20 +41,12 @@ def build_tb_parser_model(
 
     tok2vec (Model[List[Doc], List[Floats2d]]):
         Subnetwork to map tokens into vector representations.
-    nr_feature_tokens (int): The number of tokens in the context to use to
+    state_type (str):
-        construct the state vector. Valid choices are 1, 2, 3, 6, 8 and 13. The
+        String value denoting the type of parser model: "deps" or "ner"
-        2, 8 and 13 feature sets are designed for the parser, while the 3 and 6
+    extra_state_tokens (bool): Whether or not to use additional tokens in the context
-        feature sets are designed for the NER. The recommended feature sets are
+        to construct the state vector. Defaults to `False`, which means 3 and 8
-        3 for NER, and 8 for the dependency parser.
+        for the NER and parser respectively. When set to `True`, this would become 6
-
+        feature sets (for the NER) or 13 (for the parser).
-        TODO: This feature should be split into two, state_type: ["deps", "ner"]
-        and extra_state_features: [True, False]. This would map into:
-
-        (deps, False): 8
-        (deps, True): 13
-        (ner, False): 3
-        (ner, True): 6
-
     hidden_width (int): The width of the hidden layer.
     maxout_pieces (int): How many pieces to use in the state prediction layer.
         Recommended values are 1, 2 or 3. If 1, the maxout non-linearity
@@ -68,8 +61,14 @@ def build_tb_parser_model(
         Usually inferred from data at the beginning of training, or loaded from
         disk.
     """
+    if state_type == "deps":
+        nr_feature_tokens = 13 if extra_state_tokens else 8
+    elif state_type == "ner":
+        nr_feature_tokens = 6 if extra_state_tokens else 3
+    else:
+        raise ValueError(f"unknown state type {state_type}")  # TODO error
     t2v_width = tok2vec.get_dim("nO") if tok2vec.has_dim("nO") else None
-    tok2vec = chain(tok2vec, list2array(), Linear(hidden_width, t2v_width),)
+    tok2vec = chain(tok2vec, list2array(), Linear(hidden_width, t2v_width))
     tok2vec.set_dim("nO", hidden_width)
     lower = PrecomputableAffine(
         nO=hidden_width if use_upper else nO,

spacy/pipeline/dep_parser.pyx

@@ -15,7 +15,8 @@ from ..training import validate_examples
 default_model_config = """
 [model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 8
+state_type = "deps"
+extra_state_tokens = false
 hidden_width = 64
 maxout_pieces = 2
 

spacy/pipeline/ner.pyx

@@ -13,7 +13,8 @@ from ..training import validate_examples
 default_model_config = """
 [model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 6
+state_type = "ner"
+extra_state_tokens = false
 hidden_width = 64
 maxout_pieces = 2
 

spacy/tests/serialize/test_serialize_config.py

@@ -67,7 +67,8 @@ width = ${components.tok2vec.model.width}
 parser_config_string = """
 [model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 99
+state_type = "deps"
+extra_state_tokens = false
 hidden_width = 66
 maxout_pieces = 2
 
@@ -95,7 +96,11 @@ def my_parser():
         MaxoutWindowEncoder(width=321, window_size=3, maxout_pieces=4, depth=2),
     )
     parser = build_tb_parser_model(
-        tok2vec=tok2vec, nr_feature_tokens=7, hidden_width=65, maxout_pieces=5
+        tok2vec=tok2vec,
+        state_type="deps",
+        extra_state_tokens=True,
+        hidden_width=65,
+        maxout_pieces=5,
     )
     return parser
 

website/docs/api/architectures.md

@@ -414,7 +414,8 @@ one component.
 > ```ini
 > [model]
 > @architectures = "spacy.TransitionBasedParser.v1"
-> nr_feature_tokens = 6
+> state_type = "ner"
+> extra_state_tokens = false
 > hidden_width = 64
 > maxout_pieces = 2
 >
@@ -447,9 +448,10 @@ consists of either two or three subnetworks:
   as action scores directly.
 
 | Name                 | Description                                                                                                                                                                                                                                                                                                                                                             |
-| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `tok2vec`            | Subnetwork to map tokens into vector representations. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                                                                                                                                              |
-| `nr_feature_tokens` | The number of tokens in the context to use to construct the state vector. Valid choices are `1`, `2`, `3`, `6`, `8` and `13`. The `2`, `8` and `13` feature sets are designed for the parser, while the `3` and `6` feature sets are designed for the entity recognizer. The recommended feature sets are `3` for NER, and `8` for the dependency parser. ~~int~~       |
+| `state_type`         | Which task to extract features for. Possible values are "ner" and "dependencies". ~~str~~                                                                                                                                                                                                                                                                               |
+| `extra_state_tokens` | Whether to use an expanded feature set when extracting the state tokens. Slightly slower, but sometimes improves accuracy slightly. Defaults to `False`. ~~bool~~                                                                                                                                                                                                       |
 | `hidden_width`       | The width of the hidden layer. ~~int~~                                                                                                                                                                                                                                                                                                                                  |
 | `maxout_pieces`      | How many pieces to use in the state prediction layer. Recommended values are `1`, `2` or `3`. If `1`, the maxout non-linearity is replaced with a [`Relu`](https://thinc.ai/docs/api-layers#relu) non-linearity if `use_upper` is `True`, and no non-linearity if `False`. ~~int~~                                                                                      |
 | `use_upper`          | Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to `False` for large pretrained models such as transformers, and `True` for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. ~~bool~~ |

website/docs/usage/embeddings-transformers.md

@@ -448,7 +448,8 @@ factory = "ner"
 
 [nlp.pipeline.ner.model]
 @architectures = "spacy.TransitionBasedParser.v1"
-nr_feature_tokens = 3
+state_type = "ner"
+extra_state_tokens = false
 hidden_width = 128
 maxout_pieces = 3
 use_upper = false