Update NEL emerson config options (#207)

* remove ner from pipeline

* fix scoring weights

* two configs, one with entity_ruler and one with ner

* add config with NEL only, training should work with this

* restore pipeline creation

* restore vectors_model

* revert change to benchmark EL project

tutorials/nel_emerson/configs/nel.cfg → tutorials/nel_emerson/configs/nel_entityruler.cfg

@@ -13,7 +13,7 @@ gpu_allocator = null
 
 [nlp]
 lang = "en"
-pipeline = ["sentencizer","entity_ruler","ner","entity_linker"]
+pipeline = ["sentencizer","entity_ruler","entity_linker"]
 disabled = []
 before_creation = null
 after_creation = null
@@ -30,10 +30,6 @@ punct_chars = null
 source = "${paths.base_nlp}"
 component = "entity_ruler"
 
-[components.ner]
-source = "${paths.base_nlp}"
-component = "ner"
-
 [components.entity_linker]
 factory = "entity_linker"
 entity_vector_length = 64
@@ -94,7 +90,7 @@ eval_frequency = 200
 accumulate_gradient = 2
 max_epochs = 0
 max_steps = 600
-frozen_components = ["sentencizer","ner"]
+frozen_components = []
 before_to_disk = null
 
 [training.logger]
@@ -130,6 +126,12 @@ learn_rate = 0.001
 nel_micro_p = 0.0
 nel_micro_r = 0.0
 nel_micro_f = 1.0
+ents_f = 0.0
+ents_p = 0.0
+ents_r = 0.0
+sents_f = null
+sents_p = null
+sents_r = null
 
 [pretraining]
 

tutorials/nel_emerson/configs/nel_ner.cfg

@@ -0,0 +1,148 @@
+[paths]
+train = ""
+dev = ""
+raw = null
+init_tok2vec = null
+kb = ""
+base_nlp = ""
+vectors = "${paths.base_nlp}"
+
+[system]
+seed = 342
+gpu_allocator = null
+
+[nlp]
+lang = "en"
+pipeline = ["sentencizer","ner","entity_linker"]
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[components.sentencizer]
+factory = "sentencizer"
+punct_chars = null
+
+[components.ner]
+source = "${paths.base_nlp}"
+component = "ner"
+
+[components.entity_linker]
+factory = "entity_linker"
+entity_vector_length = 64
+get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
+incl_context = true
+incl_prior = true
+labels_discard = []
+use_gold_ents = true
+
+[components.entity_linker.model]
+@architectures = "spacy.EntityLinker.v2"
+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
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+
+[initialize.components]
+
+[initialize.components.entity_linker]
+
+[initialize.components.entity_linker.kb_loader]
+@misc = "spacy.KBFromFile.v1"
+kb_path = ${paths.kb}
+
+[initialize.tokenizer]
+
+
+[corpora]
+
+[corpora.train]
+@readers = "MyCorpus.v1"
+file = ${paths.train}
+
+[corpora.dev]
+@readers = "MyCorpus.v1"
+file = ${paths.dev}
+
+[training]
+train_corpus = "corpora.train"
+dev_corpus = "corpora.dev"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.2
+patience = 10000
+eval_frequency = 200
+accumulate_gradient = 2
+max_epochs = 0
+max_steps = 600
+frozen_components = ["ner"]
+before_to_disk = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[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]
+nel_micro_p = 0.0
+nel_micro_r = 0.0
+nel_micro_f = 1.0
+ents_f = 0.0
+ents_p = 0.0
+ents_r = 0.0
+sents_f = null
+sents_p = null
+sents_r = null
+
+[pretraining]
+
+[optimizer]
+@optimizers = "Adam.v1"
+learn_rate = 0.001
+beta1 = 0.9
+beta2 = 0.999
+L2 = 0.0
+eps = 0.00000001
+grad_clip = 1.0
+L2_is_weight_decay = true
+use_averages = true

tutorials/nel_emerson/configs/nel_only.cfg

@@ -0,0 +1,141 @@
+[paths]
+train = ""
+dev = ""
+raw = null
+init_tok2vec = null
+kb = ""
+base_nlp = ""
+vectors = "${paths.base_nlp}"
+
+[system]
+seed = 342
+gpu_allocator = null
+
+[nlp]
+lang = "en"
+pipeline = ["sentencizer","entity_linker"]
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[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 = []
+use_gold_ents = true
+
+[components.entity_linker.model]
+@architectures = "spacy.EntityLinker.v2"
+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
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+
+[initialize.components]
+
+[initialize.components.entity_linker]
+
+[initialize.components.entity_linker.kb_loader]
+@misc = "spacy.KBFromFile.v1"
+kb_path = ${paths.kb}
+
+[initialize.tokenizer]
+
+
+[corpora]
+
+[corpora.train]
+@readers = "MyCorpus.v1"
+file = ${paths.train}
+
+[corpora.dev]
+@readers = "MyCorpus.v1"
+file = ${paths.dev}
+
+[training]
+train_corpus = "corpora.train"
+dev_corpus = "corpora.dev"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.2
+patience = 10000
+eval_frequency = 200
+accumulate_gradient = 2
+max_epochs = 0
+max_steps = 600
+frozen_components = []
+before_to_disk = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[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]
+nel_micro_p = 0.0
+nel_micro_r = 0.0
+nel_micro_f = 1.0
+sents_f = null
+sents_p = null
+sents_r = null
+
+[pretraining]
+
+[optimizer]
+@optimizers = "Adam.v1"
+learn_rate = 0.001
+beta1 = 0.9
+beta2 = 0.999
+L2 = 0.0
+eps = 0.00000001
+grad_clip = 1.0
+L2_is_weight_decay = true
+use_averages = true

tutorials/nel_emerson/project.yml

@@ -3,15 +3,15 @@ description: "**This project was created as part of a [step-by-step video tutori
 # Variables can be referenced across the project.yml using ${vars.var_name}
 vars:
   name: "nel_emerson"
-  config: "nel.cfg"
+  config: "nel_entityruler.cfg"
   vectors_model: "en_core_web_md"
   annotations: "emerson_annotated_text.jsonl"
   entities: "entities.csv"
   kb: "my_kb"
   nlp: "my_nlp"
   train: "train"
   dev: "dev"
-  version: "0.0.3"
+  version: "0.0.4"
 
 # These are the directories that the project needs. The project CLI will make
 # sure that they always exist.