import sling
import sling.flags as flags
import sling.task.workflow as workflow
flags.define("--crf", default=False, action='store_true')
flags.parse()
# Start up workflow system.
workflow.startup()
# Create workflow.
wf = workflow.Workflow("bio-training")
# Parser trainer inputs and outputs.
kb = wf.resource(
#"local/data/e/wiki/kb.sling",
"data/dev/types.sling",
format="store/frame")
training_corpus = wf.resource("local/data/e/silver/en/[email protected]",
format="record/document")
evaluation_corpus = wf.resource("local/data/e/silver/en/eval.rec",
format="record/document")
vocabulary = wf.resource("local/data/e/silver/en/vocabulary.map",
format="textmap/word")
parser_model = wf.resource("local/data/e/knolex/" +
("bio" if flags.arg.crf else "crf") + "-en.flow",
# limitations under the License.
"""Build FactGrid knowledge base and alias tables."""
import sling
import sling.flags as flags
import sling.task.workflow as workflow
import sling.task.data as data
flags.parse()
# Start up workflow system.
workflow.startup()
# Create workflow.
wf = workflow.Workflow("factgrid")
datasets = data.Datasets(wf)
# Resources.
def res(files, fmt="records/frame"):
return wf.resource(files, format=fmt)
fgdir = "data/e/factgrid"
fg_items = res(fgdir + "/factgrid-items.rec")
fg_properties = res(fgdir + "/factgrid-properties.rec")
items = res(fgdir + "/items.rec")
fanin = res(fgdir + "/fanin.rec")
xrefs = res(fgdir + "/xrefs.sling", "store/frame")
xref_config = res("data/factgrid/xrefs.sling", "store/frame")
recon_config = res("data/factgrid/recon.sling", "store/frame")
fg_kb = res(fgdir + "/factgrid-kb.sling", "store/frame")
import sling
import sling.flags as flags
import sling.task.workflow as workflow
# Start up workflow system.
flags.parse()
workflow.startup()
# Create workflow.
wf = workflow.Workflow("parser-training")
# Parser trainer inputs and outputs.
training_corpus = wf.resource("local/data/corpora/caspar/train_shuffled.rec",
format="record/document")
evaluation_corpus = wf.resource("local/data/corpora/caspar/dev.rec",
format="record/document")
word_embeddings = wf.resource(
"local/data/corpora/caspar/word2vec-32-embeddings.bin",
format="embeddings")
parser_model = wf.resource("local/data/e/caspar/caspar.flow", format="flow")
# Parser trainer task.
trainer = wf.task("caspar-trainer")
trainer.add_params({
"learning_rate": 1.0,
"learning_rate_decay": 0.8,
"clipping": 1,
flags.parse()
if flags.arg.accurate:
modelfn = "local/data/e/caspar/caspar-accurate.flow"
rnn_layers = 3
rnn_dim = 192
else:
modelfn = "local/data/e/caspar/caspar.flow"
rnn_layers = 1
rnn_dim = 128
# Start up workflow system.
workflow.startup()
# Create workflow.
wf = workflow.Workflow("caspar-trainer")
# Parser trainer inputs and outputs.
training_corpus = wf.resource("local/data/corpora/caspar/train_shuffled.rec",
format="record/document")
evaluation_corpus = wf.resource("local/data/corpora/caspar/dev.rec",
format="record/document")
word_embeddings = wf.resource(
"local/data/corpora/caspar/word2vec-32-embeddings.bin",
format="embeddings")
parser_model = wf.resource(modelfn, format="flow")
# Parser trainer task.
decoder = "bio"
elif flags.arg.bio:
parser_name = "bio"
decoder = "bio"
elif flags.arg.biaf:
parser_name = "biaf"
decoder = "biaffine"
else:
parser_name = "caspar"
decoder = "caspar"
# Start up workflow system.
workflow.startup()
# Create workflow.
wf = workflow.Workflow("conll-training")
# Parser trainer inputs and outputs.
kb = wf.resource("data/dev/conll.sling", format="store/frame")
training_corpus = wf.resource("data/c/conll2003/train.rec",
format="record/document")
evaluation_corpus = wf.resource("data/c/conll2003/eval.rec",
format="record/document")
parser_model = wf.resource("data/e/conll/" + parser_name + ".flow",
format="flow")
# Parser trainer task.
trainer = wf.task("parser-trainer")
import sling
import sling.flags as flags
import sling.task.workflow as workflow
flags.parse()
# Start up workflow system.
workflow.startup()
# Create workflow.
wf = workflow.Workflow("knolex-training")
# Parser trainer inputs and outputs.
kb = wf.resource("data/e/kb/kb.sling", format="store/frame")
training_corpus = wf.resource("data/e/silver/en/[email protected]",
format="record/document")
evaluation_corpus = wf.resource("data/e/silver/en/eval.rec",
format="record/document")
vocabulary = wf.resource("data/e/silver/en/vocabulary.map",
format="textmap/word")
parser_model = wf.resource("data/e/knolex/knolex-en.flow", format="flow")
# Parser trainer task.
trainer = wf.task("parser-trainer")
trainer.add_params({
"encoder": "lexrnn",
import sling
import sling.flags as flags
import sling.task.workflow as workflow
flags.parse()
# Start up workflow system.
workflow.startup()
# Create workflow.
wf = workflow.Workflow("biaf-training")
# Parser trainer inputs and outputs.
kb = wf.resource(
#"data/e/kb/kb.sling",
"data/dev/types.sling",
format="store/frame")
training_corpus = wf.resource("data/e/silver/en/[email protected]",
format="record/document")
evaluation_corpus = wf.resource("data/e/silver/en/eval.rec",
format="record/document")
vocabulary = wf.resource("data/e/silver/en/vocabulary.map",
format="textmap/word")
parser_model = wf.resource("data/e/knolex/biaf-en.flow", format="flow")
# Parser trainer task.
trainer = wf.task("parser-trainer")
