From 377108998a4dc25fb23df8d6cd813f1ac85b0a3f Mon Sep 17 00:00:00 2001 From: Matthw Honnibal Date: Sat, 18 Jul 2020 01:26:07 +0200 Subject: [PATCH] Add config for joint dep pos --- examples/experiments/joint-dep-pos.cfg | 78 ++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 examples/experiments/joint-dep-pos.cfg diff --git a/examples/experiments/joint-dep-pos.cfg b/examples/experiments/joint-dep-pos.cfg new file mode 100644 index 000000000..ea960972a --- /dev/null +++ b/examples/experiments/joint-dep-pos.cfg @@ -0,0 +1,78 @@ +[training] +patience = 10000 +eval_frequency = 50 +dropout = 0.2 +init_tok2vec = null +vectors = null +max_epochs = 100 +orth_variant_level = 0.0 +gold_preproc = true +max_length = 0 +use_gpu = -1 +scores = ["tags_acc", "uas", "las"] +score_weights = {"las": 0.8, "tags_acc": 0.2} +limit = 0 +seed = 0 +accumulate_gradient = 1 +discard_oversize = false +batch_size = 1000 +batch_by = "words" + +#[training.batch_size] +#@schedules = "compounding.v1" +#start = 100 +#stop = 1000 +#compound = 1.001 + +[training.optimizer] +@optimizers = "Adam.v1" +learn_rate = 0.001 +beta1 = 0.9 +beta2 = 0.999 + +[nlp] +lang = "en" +vectors = ${training:vectors} + +[nlp.pipeline] + +[nlp.pipeline.tok2vec] +factory = "tok2vec" + +[nlp.pipeline.tagger] +factory = "tagger" + +[nlp.pipeline.parser] +factory = "parser" +learn_tokens = false +min_action_freq = 1 +beam_width = 1 +beam_update_prob = 1.0 + +[nlp.pipeline.tagger.model] +@architectures = "spacy.Tagger.v1" + +[nlp.pipeline.tagger.model.tok2vec] +@architectures = "spacy.Tok2VecTensors.v1" +width = ${nlp.pipeline.tok2vec.model:width} + +[nlp.pipeline.parser.model] +@architectures = "spacy.TransitionBasedParser.v1" +nr_feature_tokens = 8 +hidden_width = 64 +maxout_pieces = 3 + +[nlp.pipeline.parser.model.tok2vec] +@architectures = "spacy.Tok2VecTensors.v1" +width = ${nlp.pipeline.tok2vec.model:width} + +[nlp.pipeline.tok2vec.model] +@architectures = "spacy.HashEmbedCNN.v1" +pretrained_vectors = ${nlp:vectors} +width = 128 +depth = 4 +window_size = 1 +embed_size = 2000 +maxout_pieces = 3 +subword_features = true +dropout = null