def extract_named_entities():
# Extract Wikipedia link graph.
if flags.arg.extract_wikilinks:
log.info("Extract Wikipedia link graph")
wf = entity.EntityWorkflow("wiki-links")
wf.extract_wikilinks()
workflow.run(wf.wf)
# Extract IDF table.
if flags.arg.build_idf:
wf = entity.EntityWorkflow("idf-table")
for language in flags.arg.languages:
log.info("Build " + language + " IDF table")
wf.build_idf(language=language)
workflow.run(wf.wf)
# Fuse NER items.
if flags.arg.fuse_ner_items:
log.info("Fuse NER items")
wf = entity.EntityWorkflow("fuse-ner-items")
wf.fuse_items()
workflow.run(wf.wf)
# Build NER knowledge base.
if flags.arg.build_ner_kb:
log.info("Build NER knowledge base")
wf = entity.EntityWorkflow("ner-knowledge-base")
wf.build_knowledge_base()
workflow.run(wf.wf)
def sling_entity_link(sling_input_corpus, sling_output_corpus):
"""Does sling entity linking and created linked output corpus."""
labeler = entity.EntityWorkflow("wiki-label")
unannotated = labeler.wf.resource(sling_input_corpus,
format="records/document")
annotated = labeler.wf.resource(sling_output_corpus,
format="records/document")
labeler.label_documents(indocs=unannotated, outdocs=annotated)
workflow.run(labeler.wf)