Errors in config when trying to train NER and Relation Extraction together

[apatel415]

Hi Team,

I am trying to train a NER and Relation Extraction model together using the model provided here python -m spacy project clone tutorials/rel_component. In the video, Sofie mentioned that we would need to include the NER component in the config file but I am unsure how to do so.

I took the config file that was provided and just added the NER components to it. However, when I try to train the model, I get the following error:

=========================== Initializing pipeline ===========================
✘ Config validation error
Bad value substitution: option 'width' in section 'components.ner.model.tok2vec' contains an interpolation key 'components.tok2vec.model.encode.width' which is not a valid option name. Raw value: '${components.tok2vec.model.encode.width}'

For reference, here is my config file below:

[paths]
train = null
dev = null
raw = null
init_tok2vec = null

[system]
seed = 342
gpu_allocator = null

[nlp]
lang = "en"
pipeline = ["tok2vec", "ner", "relation_extractor"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
batch_size = 1000

[components]

[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
update_with_oracle_cut_size = 100

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.tok2vec]
factory = "tok2vec"

[components.tok2vec.model]
@architectures = "spacy.HashEmbedCNN.v1"
pretrained_vectors = null
width = 96
depth = 2
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true

[components.relation_extractor]
factory = "relation_extractor"
threshold = 0.5

[components.relation_extractor.model]
@architectures = "rel_model.v1"

[components.relation_extractor.model.create_instance_tensor]
@architectures = "rel_instance_tensor.v1"

[components.relation_extractor.model.create_instance_tensor.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.width}

[components.relation_extractor.model.create_instance_tensor.pooling]
@layers = "reduce_mean.v1"

[components.relation_extractor.model.create_instance_tensor.get_instances]
@misc = "rel_instance_generator.v1"
max_length = 20

[components.relation_extractor.model.classification_layer]
@architectures = "rel_classification_layer.v1"
nI = null
nO = null

[initialize]

[initialize.components]

[corpora]

[corpora.dev]
@readers = "Gold_ents_Corpus.v1"
file = ${paths.dev}

[corpora.train]
@readers = "Gold_ents_Corpus.v1"
file = ${paths.train}

[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600000
max_epochs = 0
max_steps = 10000
eval_frequency = 500
frozen_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
logger = {"@loggers":"spacy.ConsoleLogger.v1"}

[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001

[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
rel_micro_p = 0.0
rel_micro_r = 0.0
rel_micro_f = 1.0

[polm]

Your Markdown isn't correct, please check the Github guide and use the preview function to make it easier for us to help you.

Like the error states, the name you have isn't valid, because the particular field is not in your config. If you look you will see that width is in your config, but the location in the config file has no encode in it. If you remove encode I would expect it to work.

[apatel415]

Silly mistake, thank you! Was able to resolve and train.