Created
March 13, 2020 16:50
-
-
Save zredlined/2840f74b1d7b7d05880a3a77c67c5ad8 to your computer and use it in GitHub Desktop.
example ontonotes5 converted to spacy training format
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"id": "fake", | |
"paragraphs": [ | |
{ | |
"raw": "Israel has blockaded all West Bank cities after 10 people died in one of the worst days of Israeli-Palestinian violence in more than 10 weeks. Israeli tank-fire killed five Palestinians including four policemen in the West Bank town of Jenine. Israeli forces killed one Palestinian near Bethlehem and another in Arab East Jerusalem. Palestinian gunmen in the West Bank killed two Jewish settlers in a roadside ambush near Hebron and a third Israeli in an attack against a bus outside of Jericho.", | |
"sentences": [ | |
{ | |
"tokens": [ | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 0, | |
"ner": "U-GPE", | |
"orth": "Israel ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 1, | |
"ner": "O", | |
"orth": "has ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 2, | |
"ner": "O", | |
"orth": "blockaded ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 3, | |
"ner": "O", | |
"orth": "all ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 4, | |
"ner": "B-GPE", | |
"orth": "West ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 5, | |
"ner": "L-GPE", | |
"orth": "Bank ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 6, | |
"ner": "O", | |
"orth": "cities ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 7, | |
"ner": "O", | |
"orth": "after ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 8, | |
"ner": "U-CARDINAL", | |
"orth": "10 ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 9, | |
"ner": "O", | |
"orth": "people ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 10, | |
"ner": "O", | |
"orth": "died ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 11, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 12, | |
"ner": "U-CARDINAL", | |
"orth": "one ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 13, | |
"ner": "O", | |
"orth": "of ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 14, | |
"ner": "B-DATE", | |
"orth": "the ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 15, | |
"ner": "I-DATE", | |
"orth": "worst ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 16, | |
"ner": "L-DATE", | |
"orth": "days ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 17, | |
"ner": "O", | |
"orth": "of ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 18, | |
"ner": "U-NORP", | |
"orth": "Israeli ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 19, | |
"ner": "O", | |
"orth": "- ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 20, | |
"ner": "O", | |
"orth": "Palestinian ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 21, | |
"ner": "O", | |
"orth": "violence ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 22, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 23, | |
"ner": "B-DATE", | |
"orth": "more ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 24, | |
"ner": "I-DATE", | |
"orth": "than ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 25, | |
"ner": "I-DATE", | |
"orth": "10 ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 26, | |
"ner": "L-DATE", | |
"orth": "weeks ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 27, | |
"ner": "O", | |
"orth": ".", | |
"tag": "" | |
} | |
] | |
}, | |
{ | |
"tokens": [ | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 0, | |
"ner": "U-NORP", | |
"orth": "Israeli ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 1, | |
"ner": "O", | |
"orth": "tank ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 2, | |
"ner": "O", | |
"orth": "- ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 3, | |
"ner": "O", | |
"orth": "fire ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 4, | |
"ner": "O", | |
"orth": "killed ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 5, | |
"ner": "U-CARDINAL", | |
"orth": "five ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 6, | |
"ner": "U-NORP", | |
"orth": "Palestinians ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 7, | |
"ner": "O", | |
"orth": "including ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 8, | |
"ner": "U-CARDINAL", | |
"orth": "four ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 9, | |
"ner": "O", | |
"orth": "policemen ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 10, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 11, | |
"ner": "O", | |
"orth": "the ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 12, | |
"ner": "B-GPE", | |
"orth": "West ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 13, | |
"ner": "L-GPE", | |
"orth": "Bank ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 14, | |
"ner": "O", | |
"orth": "town ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 15, | |
"ner": "O", | |
"orth": "of ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 16, | |
"ner": "U-GPE", | |
"orth": "Jenine ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 17, | |
"ner": "O", | |
"orth": ".", | |
"tag": "" | |
} | |
] | |
}, | |
{ | |
"tokens": [ | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 0, | |
"ner": "U-NORP", | |
"orth": "Israeli ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 1, | |
"ner": "O", | |
"orth": "forces ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 2, | |
"ner": "O", | |
"orth": "killed ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 3, | |
"ner": "U-CARDINAL", | |
"orth": "one ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 4, | |
"ner": "U-NORP", | |
"orth": "Palestinian ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 5, | |
"ner": "O", | |
"orth": "near ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 6, | |
"ner": "U-GPE", | |
"orth": "Bethlehem ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 7, | |
"ner": "O", | |
"orth": "and ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 8, | |
"ner": "O", | |
"orth": "another ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 9, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 10, | |
"ner": "U-NORP", | |
"orth": "Arab ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 11, | |
"ner": "B-GPE", | |
"orth": "East ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 12, | |
"ner": "L-GPE", | |
"orth": "Jerusalem ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 13, | |
"ner": "O", | |
"orth": ".", | |
"tag": "" | |
} | |
] | |
}, | |
{ | |
"tokens": [ | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 0, | |
"ner": "U-NORP", | |
"orth": "Palestinian ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 1, | |
"ner": "O", | |
"orth": "gunmen ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 2, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 3, | |
"ner": "B-GPE", | |
"orth": "the ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 4, | |
"ner": "I-GPE", | |
"orth": "West ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 5, | |
"ner": "L-GPE", | |
"orth": "Bank ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 6, | |
"ner": "O", | |
"orth": "killed ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 7, | |
"ner": "U-CARDINAL", | |
"orth": "two ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 8, | |
"ner": "U-NORP", | |
"orth": "Jewish ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 9, | |
"ner": "O", | |
"orth": "settlers ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 10, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 11, | |
"ner": "O", | |
"orth": "a ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 12, | |
"ner": "O", | |
"orth": "roadside ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 13, | |
"ner": "O", | |
"orth": "ambush ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 14, | |
"ner": "O", | |
"orth": "near ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 15, | |
"ner": "U-GPE", | |
"orth": "Hebron ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 16, | |
"ner": "O", | |
"orth": "and ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 17, | |
"ner": "O", | |
"orth": "a ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 18, | |
"ner": "O", | |
"orth": "third ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 19, | |
"ner": "U-NORP", | |
"orth": "Israeli ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 20, | |
"ner": "O", | |
"orth": "in ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 21, | |
"ner": "O", | |
"orth": "an ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 22, | |
"ner": "O", | |
"orth": "attack ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 23, | |
"ner": "O", | |
"orth": "against ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 24, | |
"ner": "O", | |
"orth": "a ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 25, | |
"ner": "O", | |
"orth": "bus ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 26, | |
"ner": "O", | |
"orth": "outside ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 27, | |
"ner": "O", | |
"orth": "of ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 28, | |
"ner": "U-GPE", | |
"orth": "Jericho ", | |
"tag": "" | |
}, | |
{ | |
"dep": "", | |
"head": 0, | |
"id": 29, | |
"ner": "O", | |
"orth": ".", | |
"tag": "" | |
} | |
] | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment