for twitter status, for generic feature extraction (used on queries), for entity linking expansion.
e.g. R-0.2-100-....-terms.bigrams-terms-surfaceForms
[query numbers divided by :]
"""
import sys, errno, os
from CipCipPy.utils.io import readQueries, readQrels
from CipCipPy.filtering import SupervisedFilterer
from CipCipPy.classification import *
from CipCipPy.classification.feature import *
#FIXME use argparse
queries = readQueries(sys.argv[1])
with open(sys.argv[2]) as ann_qfile:
queriesAnnotated = json.load(ann_qfile)
if len(sys.argv) > 8:
queries = [q for q in queries if q[0] in set(sys.argv[8].split(':'))]
qrels = readQrels(sys.argv[3], set(q[0] for q in queries))
dataset_path = sys.argv[4]
resultsPath = sys.argv[5]
external = False
if sys.argv[6] == 'external':
external = True
minimum link probability, feature extraction function names (divided by .)
for twitter status, for generic feature extraction (used on queries), for entity linking expansion.
e.g. R-0.2-100-....-terms.bigrams-terms-surfaceForms
[query numbers divided by :]
"""
import sys, errno, os
from CipCipPy.utils.io import readQueries, readQrels
from CipCipPy.filtering import SupervisedFilterer
from CipCipPy.classification import *
from CipCipPy.classification.feature import *
#FIXME use argparse
queries = readQueries(sys.argv[1])
with open(sys.argv[2]) as ann_qfile:
queriesAnnotated = json.load(ann_qfile)
if len(sys.argv) > 8:
queries = [q for q in queries if q[0] in set(sys.argv[8].split(':'))]
qrels = readQrels(sys.argv[3], set(q[0] for q in queries))
dataset_path = sys.argv[4]
resultsPath = sys.argv[5]
external = False
if sys.argv[6] == 'external':
external = True