I'm training an entity linker model with spacy 3, and am getting the following error when running spacy train:
ValueError: [E030] Sentence boundaries unset. You can add the 'sentencizer' component to the pipeline with: nlp.add_pipe('sentencizer'). Alternatively, add the dependency parser or sentence recognizer, or set sentence boundaries by setting doc[i].is_sent_start. .
I've tried with both transformer and tok2vec pipelines, it seems to be failing on this line:
File "/usr/local/lib/python3.7/dist-packages/spacy/pipeline/entity_linker.py", line 252, in update sentences = [s for s in eg.reference.sents]
Running spacy debug data shows no errors.
I'm using the following config, before filling it in with spacy init fill-config:
[paths]
train = null
dev = null
kb = "./kb"
[system]
gpu_allocator = "pytorch"
[nlp]
lang = "en"
pipeline = ["transformer","parser","sentencizer","ner", "entity_linker"]
batch_size = 128
[components]
[components.transformer]
factory = "transformer"
[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "roberta-base"
tokenizer_config = {"use_fast": true}
[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.sentencizer]
factory = "sentencizer"
punct_chars = null
[components.entity_linker]
factory = "entity_linker"
entity_vector_length = 64
get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
incl_context = true
incl_prior = true
labels_discard = []
[components.entity_linker.model]
@architectures = "spacy.EntityLinker.v1"
nO = null
[components.entity_linker.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v1"
pretrained_vectors = null
width = 96
depth = 2
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true
[components.parser]
factory = "parser"
[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = false
nO = null
[components.parser.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.parser.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
[components.ner]
factory = "ner"
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = false
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.ner.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
[corpora]
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
[training]
accumulate_gradient = 3
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
[training.optimizer]
@optimizers = "Adam.v1"
[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 5e-5
[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 2000
buffer = 256
[initialize]
vectors = ${paths.vectors}
[initialize.components]
[initialize.components.sentencizer]
[initialize.components.entity_linker]
[initialize.components.entity_linker.kb_loader]
@misc = "spacy.KBFromFile.v1"
kb_path = ${paths.kb}
I can write a script to add the sentence boundaries in manually to the docs, but am wondering why the sentencizer component is not doing this for me, is there something missing in the config?