explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-22 11:59:14 +03:00
Code Issues Packages Projects Releases Wiki Activity
68ccfc4c39
spaCy/extra/example_data/textcat_example_data/jigsaw-toxic-comment.json
Ines Montani b37fdbb613 Clean out /examples and /bin
2020-08-25 13:28:42 +02:00

2987 lines
66 KiB
JSON
Raw Blame History

[
{
"id":0,
"paragraphs":[
{
"raw":"Explanation\nWhy the edits made under my username Hardcore Metallica Fan were reverted? They weren't vandalisms, just closure on some GAs after I voted at New York Dolls FAC. And please don't remove the template from the talk page since I'm retired now.89.205.38.27",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"Explanation",
"ner":"O"
},
{
"id":1,
"orth":"\n",
"ner":"O"
},
{
"id":2,
"orth":"Why",
"ner":"O"
},
{
"id":3,
"orth":"the",
"ner":"O"
},
{
"id":4,
"orth":"edits",
"ner":"O"
},
{
"id":5,
"orth":"made",
"ner":"O"
},
{
"id":6,
"orth":"under",
"ner":"O"
},
{
"id":7,
"orth":"my",
"ner":"O"
},
{
"id":8,
"orth":"username",
"ner":"O"
},
{
"id":9,
"orth":"Hardcore",
"ner":"O"
},
{
"id":10,
"orth":"Metallica",
"ner":"O"
},
{
"id":11,
"orth":"Fan",
"ner":"O"
},
{
"id":12,
"orth":"were",
"ner":"O"
},
{
"id":13,
"orth":"reverted",
"ner":"O"
},
{
"id":14,
"orth":"?",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":15,
"orth":"They",
"ner":"O"
},
{
"id":16,
"orth":"were",
"ner":"O"
},
{
"id":17,
"orth":"n't",
"ner":"O"
},
{
"id":18,
"orth":"vandalisms",
"ner":"O"
},
{
"id":19,
"orth":",",
"ner":"O"
},
{
"id":20,
"orth":"just",
"ner":"O"
},
{
"id":21,
"orth":"closure",
"ner":"O"
},
{
"id":22,
"orth":"on",
"ner":"O"
},
{
"id":23,
"orth":"some",
"ner":"O"
},
{
"id":24,
"orth":"GAs",
"ner":"O"
},
{
"id":25,
"orth":"after",
"ner":"O"
},
{
"id":26,
"orth":"I",
"ner":"O"
},
{
"id":27,
"orth":"voted",
"ner":"O"
},
{
"id":28,
"orth":"at",
"ner":"O"
},
{
"id":29,
"orth":"New",
"ner":"O"
},
{
"id":30,
"orth":"York",
"ner":"O"
},
{
"id":31,
"orth":"Dolls",
"ner":"O"
},
{
"id":32,
"orth":"FAC",
"ner":"O"
},
{
"id":33,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":34,
"orth":"And",
"ner":"O"
},
{
"id":35,
"orth":"please",
"ner":"O"
},
{
"id":36,
"orth":"do",
"ner":"O"
},
{
"id":37,
"orth":"n't",
"ner":"O"
},
{
"id":38,
"orth":"remove",
"ner":"O"
},
{
"id":39,
"orth":"the",
"ner":"O"
},
{
"id":40,
"orth":"template",
"ner":"O"
},
{
"id":41,
"orth":"from",
"ner":"O"
},
{
"id":42,
"orth":"the",
"ner":"O"
},
{
"id":43,
"orth":"talk",
"ner":"O"
},
{
"id":44,
"orth":"page",
"ner":"O"
},
{
"id":45,
"orth":"since",
"ner":"O"
},
{
"id":46,
"orth":"I",
"ner":"O"
},
{
"id":47,
"orth":"'m",
"ner":"O"
},
{
"id":48,
"orth":"retired",
"ner":"O"
},
{
"id":49,
"orth":"now.89.205.38.27",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":0
}
]
},
{
"raw":"I'm Sorry \n\nI'm sorry I screwed around with someones talk page. It was very bad to do. I know how having the templates on their talk page helps you assert your dominance over them. I know I should bow down to the almighty administrators. But then again, I'm going to go play outside....with your mom. 76.122.79.82",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"I",
"ner":"O"
},
{
"id":1,
"orth":"'m",
"ner":"O"
},
{
"id":2,
"orth":"Sorry",
"ner":"O"
},
{
"id":3,
"orth":"\n\n",
"ner":"O"
},
{
"id":4,
"orth":"I",
"ner":"O"
},
{
"id":5,
"orth":"'m",
"ner":"O"
},
{
"id":6,
"orth":"sorry",
"ner":"O"
},
{
"id":7,
"orth":"I",
"ner":"O"
},
{
"id":8,
"orth":"screwed",
"ner":"O"
},
{
"id":9,
"orth":"around",
"ner":"O"
},
{
"id":10,
"orth":"with",
"ner":"O"
},
{
"id":11,
"orth":"someones",
"ner":"O"
},
{
"id":12,
"orth":"talk",
"ner":"O"
},
{
"id":13,
"orth":"page",
"ner":"O"
},
{
"id":14,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":15,
"orth":" ",
"ner":"O"
},
{
"id":16,
"orth":"It",
"ner":"O"
},
{
"id":17,
"orth":"was",
"ner":"O"
},
{
"id":18,
"orth":"very",
"ner":"O"
},
{
"id":19,
"orth":"bad",
"ner":"O"
},
{
"id":20,
"orth":"to",
"ner":"O"
},
{
"id":21,
"orth":"do",
"ner":"O"
},
{
"id":22,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":23,
"orth":" ",
"ner":"O"
},
{
"id":24,
"orth":"I",
"ner":"O"
},
{
"id":25,
"orth":"know",
"ner":"O"
},
{
"id":26,
"orth":"how",
"ner":"O"
},
{
"id":27,
"orth":"having",
"ner":"O"
},
{
"id":28,
"orth":"the",
"ner":"O"
},
{
"id":29,
"orth":"templates",
"ner":"O"
},
{
"id":30,
"orth":"on",
"ner":"O"
},
{
"id":31,
"orth":"their",
"ner":"O"
},
{
"id":32,
"orth":"talk",
"ner":"O"
},
{
"id":33,
"orth":"page",
"ner":"O"
},
{
"id":34,
"orth":"helps",
"ner":"O"
},
{
"id":35,
"orth":"you",
"ner":"O"
},
{
"id":36,
"orth":"assert",
"ner":"O"
},
{
"id":37,
"orth":"your",
"ner":"O"
},
{
"id":38,
"orth":"dominance",
"ner":"O"
},
{
"id":39,
"orth":"over",
"ner":"O"
},
{
"id":40,
"orth":"them",
"ner":"O"
},
{
"id":41,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":42,
"orth":" ",
"ner":"O"
},
{
"id":43,
"orth":"I",
"ner":"O"
},
{
"id":44,
"orth":"know",
"ner":"O"
},
{
"id":45,
"orth":"I",
"ner":"O"
},
{
"id":46,
"orth":"should",
"ner":"O"
},
{
"id":47,
"orth":"bow",
"ner":"O"
},
{
"id":48,
"orth":"down",
"ner":"O"
},
{
"id":49,
"orth":"to",
"ner":"O"
},
{
"id":50,
"orth":"the",
"ner":"O"
},
{
"id":51,
"orth":"almighty",
"ner":"O"
},
{
"id":52,
"orth":"administrators",
"ner":"O"
},
{
"id":53,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":54,
"orth":" ",
"ner":"O"
},
{
"id":55,
"orth":"But",
"ner":"O"
},
{
"id":56,
"orth":"then",
"ner":"O"
},
{
"id":57,
"orth":"again",
"ner":"O"
},
{
"id":58,
"orth":",",
"ner":"O"
},
{
"id":59,
"orth":"I",
"ner":"O"
},
{
"id":60,
"orth":"'m",
"ner":"O"
},
{
"id":61,
"orth":"going",
"ner":"O"
},
{
"id":62,
"orth":"to",
"ner":"O"
},
{
"id":63,
"orth":"go",
"ner":"O"
},
{
"id":64,
"orth":"play",
"ner":"O"
},
{
"id":65,
"orth":"outside",
"ner":"O"
},
{
"id":66,
"orth":"....",
"ner":"O"
},
{
"id":67,
"orth":"with",
"ner":"O"
},
{
"id":68,
"orth":"your",
"ner":"O"
},
{
"id":69,
"orth":"mom",
"ner":"O"
},
{
"id":70,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":71,
"orth":" ",
"ner":"O"
},
{
"id":72,
"orth":"76.122.79.82",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":1
}
]
},
{
"raw":"Stupid peace of shit stop deleting my stuff asshole go die and fall in a hole go to hell!",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"Stupid",
"ner":"O"
},
{
"id":1,
"orth":"peace",
"ner":"O"
},
{
"id":2,
"orth":"of",
"ner":"O"
},
{
"id":3,
"orth":"shit",
"ner":"O"
},
{
"id":4,
"orth":"stop",
"ner":"O"
},
{
"id":5,
"orth":"deleting",
"ner":"O"
},
{
"id":6,
"orth":"my",
"ner":"O"
},
{
"id":7,
"orth":"stuff",
"ner":"O"
},
{
"id":8,
"orth":"asshole",
"ner":"O"
},
{
"id":9,
"orth":"go",
"ner":"O"
},
{
"id":10,
"orth":"die",
"ner":"O"
},
{
"id":11,
"orth":"and",
"ner":"O"
},
{
"id":12,
"orth":"fall",
"ner":"O"
},
{
"id":13,
"orth":"in",
"ner":"O"
},
{
"id":14,
"orth":"a",
"ner":"O"
},
{
"id":15,
"orth":"hole",
"ner":"O"
},
{
"id":16,
"orth":"go",
"ner":"O"
},
{
"id":17,
"orth":"to",
"ner":"O"
},
{
"id":18,
"orth":"hell",
"ner":"O"
},
{
"id":19,
"orth":"!",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":1
},
{
"label":"obscene",
"value":1
},
{
"label":"severe_toxic",
"value":1
},
{
"label":"toxic",
"value":1
}
]
},
{
"raw":"D'aww! He matches this background colour I'm seemingly stuck with. Thanks. (talk) 21:51, January 11, 2016 (UTC)",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"D'aww",
"ner":"O"
},
{
"id":1,
"orth":"!",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":2,
"orth":"He",
"ner":"O"
},
{
"id":3,
"orth":"matches",
"ner":"O"
},
{
"id":4,
"orth":"this",
"ner":"O"
},
{
"id":5,
"orth":"background",
"ner":"O"
},
{
"id":6,
"orth":"colour",
"ner":"O"
},
{
"id":7,
"orth":"I",
"ner":"O"
},
{
"id":8,
"orth":"'m",
"ner":"O"
},
{
"id":9,
"orth":"seemingly",
"ner":"O"
},
{
"id":10,
"orth":"stuck",
"ner":"O"
},
{
"id":11,
"orth":"with",
"ner":"O"
},
{
"id":12,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":13,
"orth":"Thanks",
"ner":"O"
},
{
"id":14,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":15,
"orth":" ",
"ner":"O"
},
{
"id":16,
"orth":"(",
"ner":"O"
},
{
"id":17,
"orth":"talk",
"ner":"O"
},
{
"id":18,
"orth":")",
"ner":"O"
},
{
"id":19,
"orth":"21:51",
"ner":"O"
},
{
"id":20,
"orth":",",
"ner":"O"
},
{
"id":21,
"orth":"January",
"ner":"O"
},
{
"id":22,
"orth":"11",
"ner":"O"
},
{
"id":23,
"orth":",",
"ner":"O"
},
{
"id":24,
"orth":"2016",
"ner":"O"
},
{
"id":25,
"orth":"(",
"ner":"O"
},
{
"id":26,
"orth":"UTC",
"ner":"O"
},
{
"id":27,
"orth":")",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":0
}
]
},
{
"raw":"GET FUCKED UP. GET FUCKEEED UP. GOT A DRINK THAT YOU CANT PUT DOWN???/ GET FUCK UP GET FUCKED UP. I'M FUCKED UP RIGHT NOW!",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"GET",
"ner":"O"
},
{
"id":1,
"orth":"FUCKED",
"ner":"O"
},
{
"id":2,
"orth":"UP",
"ner":"O"
},
{
"id":3,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":4,
"orth":"GET",
"ner":"O"
},
{
"id":5,
"orth":"FUCKEEED",
"ner":"O"
},
{
"id":6,
"orth":"UP",
"ner":"O"
},
{
"id":7,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":8,
"orth":" ",
"ner":"O"
},
{
"id":9,
"orth":"GOT",
"ner":"O"
},
{
"id":10,
"orth":"A",
"ner":"O"
},
{
"id":11,
"orth":"DRINK",
"ner":"O"
},
{
"id":12,
"orth":"THAT",
"ner":"O"
},
{
"id":13,
"orth":"YOU",
"ner":"O"
},
{
"id":14,
"orth":"CANT",
"ner":"O"
},
{
"id":15,
"orth":"PUT",
"ner":"O"
},
{
"id":16,
"orth":"DOWN???/",
"ner":"O"
},
{
"id":17,
"orth":"GET",
"ner":"O"
},
{
"id":18,
"orth":"FUCK",
"ner":"O"
},
{
"id":19,
"orth":"UP",
"ner":"O"
},
{
"id":20,
"orth":"GET",
"ner":"O"
},
{
"id":21,
"orth":"FUCKED",
"ner":"O"
},
{
"id":22,
"orth":"UP",
"ner":"O"
},
{
"id":23,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":24,
"orth":" ",
"ner":"O"
},
{
"id":25,
"orth":"I'M",
"ner":"O"
},
{
"id":26,
"orth":"FUCKED",
"ner":"O"
},
{
"id":27,
"orth":"UP",
"ner":"O"
},
{
"id":28,
"orth":"RIGHT",
"ner":"O"
},
{
"id":29,
"orth":"NOW",
"ner":"O"
},
{
"id":30,
"orth":"!",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":1
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":1
}
]
},
{
"raw":"Hey man, I'm really not trying to edit war. It's just that this guy is constantly removing relevant information and talking to me through edits instead of my talk page. He seems to care more about the formatting than the actual info.",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"Hey",
"ner":"O"
},
{
"id":1,
"orth":"man",
"ner":"O"
},
{
"id":2,
"orth":",",
"ner":"O"
},
{
"id":3,
"orth":"I",
"ner":"O"
},
{
"id":4,
"orth":"'m",
"ner":"O"
},
{
"id":5,
"orth":"really",
"ner":"O"
},
{
"id":6,
"orth":"not",
"ner":"O"
},
{
"id":7,
"orth":"trying",
"ner":"O"
},
{
"id":8,
"orth":"to",
"ner":"O"
},
{
"id":9,
"orth":"edit",
"ner":"O"
},
{
"id":10,
"orth":"war",
"ner":"O"
},
{
"id":11,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":12,
"orth":"It",
"ner":"O"
},
{
"id":13,
"orth":"'s",
"ner":"O"
},
{
"id":14,
"orth":"just",
"ner":"O"
},
{
"id":15,
"orth":"that",
"ner":"O"
},
{
"id":16,
"orth":"this",
"ner":"O"
},
{
"id":17,
"orth":"guy",
"ner":"O"
},
{
"id":18,
"orth":"is",
"ner":"O"
},
{
"id":19,
"orth":"constantly",
"ner":"O"
},
{
"id":20,
"orth":"removing",
"ner":"O"
},
{
"id":21,
"orth":"relevant",
"ner":"O"
},
{
"id":22,
"orth":"information",
"ner":"O"
},
{
"id":23,
"orth":"and",
"ner":"O"
},
{
"id":24,
"orth":"talking",
"ner":"O"
},
{
"id":25,
"orth":"to",
"ner":"O"
},
{
"id":26,
"orth":"me",
"ner":"O"
},
{
"id":27,
"orth":"through",
"ner":"O"
},
{
"id":28,
"orth":"edits",
"ner":"O"
},
{
"id":29,
"orth":"instead",
"ner":"O"
},
{
"id":30,
"orth":"of",
"ner":"O"
},
{
"id":31,
"orth":"my",
"ner":"O"
},
{
"id":32,
"orth":"talk",
"ner":"O"
},
{
"id":33,
"orth":"page",
"ner":"O"
},
{
"id":34,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":35,
"orth":"He",
"ner":"O"
},
{
"id":36,
"orth":"seems",
"ner":"O"
},
{
"id":37,
"orth":"to",
"ner":"O"
},
{
"id":38,
"orth":"care",
"ner":"O"
},
{
"id":39,
"orth":"more",
"ner":"O"
},
{
"id":40,
"orth":"about",
"ner":"O"
},
{
"id":41,
"orth":"the",
"ner":"O"
},
{
"id":42,
"orth":"formatting",
"ner":"O"
},
{
"id":43,
"orth":"than",
"ner":"O"
},
{
"id":44,
"orth":"the",
"ner":"O"
},
{
"id":45,
"orth":"actual",
"ner":"O"
},
{
"id":46,
"orth":"info",
"ner":"O"
},
{
"id":47,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":0
}
]
},
{
"raw":"\"\nMore\nI can't make any real suggestions on improvement - I wondered if the section statistics should be later on, or a subsection of \"\"types of accidents\"\" -I think the references may need tidying so that they are all in the exact same format ie date format etc. I can do that later on, if no-one else does first - if you have any preferences for formatting style on references or want to do it yourself please let me know.\n\nThere appears to be a backlog on articles for review so I guess there may be a delay until a reviewer turns up. It's listed in the relevant form eg Wikipedia:Good_article_nominations#Transport \"",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"\"",
"ner":"O"
},
{
"id":1,
"orth":"\n",
"ner":"O"
},
{
"id":2,
"orth":"More",
"ner":"O"
},
{
"id":3,
"orth":"\n",
"ner":"O"
},
{
"id":4,
"orth":"I",
"ner":"O"
},
{
"id":5,
"orth":"ca",
"ner":"O"
},
{
"id":6,
"orth":"n't",
"ner":"O"
},
{
"id":7,
"orth":"make",
"ner":"O"
},
{
"id":8,
"orth":"any",
"ner":"O"
},
{
"id":9,
"orth":"real",
"ner":"O"
},
{
"id":10,
"orth":"suggestions",
"ner":"O"
},
{
"id":11,
"orth":"on",
"ner":"O"
},
{
"id":12,
"orth":"improvement",
"ner":"O"
},
{
"id":13,
"orth":"-",
"ner":"O"
},
{
"id":14,
"orth":"I",
"ner":"O"
},
{
"id":15,
"orth":"wondered",
"ner":"O"
},
{
"id":16,
"orth":"if",
"ner":"O"
},
{
"id":17,
"orth":"the",
"ner":"O"
},
{
"id":18,
"orth":"section",
"ner":"O"
},
{
"id":19,
"orth":"statistics",
"ner":"O"
},
{
"id":20,
"orth":"should",
"ner":"O"
},
{
"id":21,
"orth":"be",
"ner":"O"
},
{
"id":22,
"orth":"later",
"ner":"O"
},
{
"id":23,
"orth":"on",
"ner":"O"
},
{
"id":24,
"orth":",",
"ner":"O"
},
{
"id":25,
"orth":"or",
"ner":"O"
},
{
"id":26,
"orth":"a",
"ner":"O"
},
{
"id":27,
"orth":"subsection",
"ner":"O"
},
{
"id":28,
"orth":"of",
"ner":"O"
},
{
"id":29,
"orth":"\"",
"ner":"O"
},
{
"id":30,
"orth":"\"",
"ner":"O"
},
{
"id":31,
"orth":"types",
"ner":"O"
},
{
"id":32,
"orth":"of",
"ner":"O"
},
{
"id":33,
"orth":"accidents",
"ner":"O"
},
{
"id":34,
"orth":"\"",
"ner":"O"
},
{
"id":35,
"orth":"\"",
"ner":"O"
},
{
"id":36,
"orth":" ",
"ner":"O"
},
{
"id":37,
"orth":"-I",
"ner":"O"
},
{
"id":38,
"orth":"think",
"ner":"O"
},
{
"id":39,
"orth":"the",
"ner":"O"
},
{
"id":40,
"orth":"references",
"ner":"O"
},
{
"id":41,
"orth":"may",
"ner":"O"
},
{
"id":42,
"orth":"need",
"ner":"O"
},
{
"id":43,
"orth":"tidying",
"ner":"O"
},
{
"id":44,
"orth":"so",
"ner":"O"
},
{
"id":45,
"orth":"that",
"ner":"O"
},
{
"id":46,
"orth":"they",
"ner":"O"
},
{
"id":47,
"orth":"are",
"ner":"O"
},
{
"id":48,
"orth":"all",
"ner":"O"
},
{
"id":49,
"orth":"in",
"ner":"O"
},
{
"id":50,
"orth":"the",
"ner":"O"
},
{
"id":51,
"orth":"exact",
"ner":"O"
},
{
"id":52,
"orth":"same",
"ner":"O"
},
{
"id":53,
"orth":"format",
"ner":"O"
},
{
"id":54,
"orth":"ie",
"ner":"O"
},
{
"id":55,
"orth":"date",
"ner":"O"
},
{
"id":56,
"orth":"format",
"ner":"O"
},
{
"id":57,
"orth":"etc",
"ner":"O"
},
{
"id":58,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":59,
"orth":"I",
"ner":"O"
},
{
"id":60,
"orth":"can",
"ner":"O"
},
{
"id":61,
"orth":"do",
"ner":"O"
},
{
"id":62,
"orth":"that",
"ner":"O"
},
{
"id":63,
"orth":"later",
"ner":"O"
},
{
"id":64,
"orth":"on",
"ner":"O"
},
{
"id":65,
"orth":",",
"ner":"O"
},
{
"id":66,
"orth":"if",
"ner":"O"
},
{
"id":67,
"orth":"no",
"ner":"O"
},
{
"id":68,
"orth":"-",
"ner":"O"
},
{
"id":69,
"orth":"one",
"ner":"O"
},
{
"id":70,
"orth":"else",
"ner":"O"
},
{
"id":71,
"orth":"does",
"ner":"O"
},
{
"id":72,
"orth":"first",
"ner":"O"
},
{
"id":73,
"orth":"-",
"ner":"O"
},
{
"id":74,
"orth":"if",
"ner":"O"
},
{
"id":75,
"orth":"you",
"ner":"O"
},
{
"id":76,
"orth":"have",
"ner":"O"
},
{
"id":77,
"orth":"any",
"ner":"O"
},
{
"id":78,
"orth":"preferences",
"ner":"O"
},
{
"id":79,
"orth":"for",
"ner":"O"
},
{
"id":80,
"orth":"formatting",
"ner":"O"
},
{
"id":81,
"orth":"style",
"ner":"O"
},
{
"id":82,
"orth":"on",
"ner":"O"
},
{
"id":83,
"orth":"references",
"ner":"O"
},
{
"id":84,
"orth":"or",
"ner":"O"
},
{
"id":85,
"orth":"want",
"ner":"O"
},
{
"id":86,
"orth":"to",
"ner":"O"
},
{
"id":87,
"orth":"do",
"ner":"O"
},
{
"id":88,
"orth":"it",
"ner":"O"
},
{
"id":89,
"orth":"yourself",
"ner":"O"
},
{
"id":90,
"orth":"please",
"ner":"O"
},
{
"id":91,
"orth":"let",
"ner":"O"
},
{
"id":92,
"orth":"me",
"ner":"O"
},
{
"id":93,
"orth":"know",
"ner":"O"
},
{
"id":94,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":95,
"orth":"\n\n",
"ner":"O"
},
{
"id":96,
"orth":"There",
"ner":"O"
},
{
"id":97,
"orth":"appears",
"ner":"O"
},
{
"id":98,
"orth":"to",
"ner":"O"
},
{
"id":99,
"orth":"be",
"ner":"O"
},
{
"id":100,
"orth":"a",
"ner":"O"
},
{
"id":101,
"orth":"backlog",
"ner":"O"
},
{
"id":102,
"orth":"on",
"ner":"O"
},
{
"id":103,
"orth":"articles",
"ner":"O"
},
{
"id":104,
"orth":"for",
"ner":"O"
},
{
"id":105,
"orth":"review",
"ner":"O"
},
{
"id":106,
"orth":"so",
"ner":"O"
},
{
"id":107,
"orth":"I",
"ner":"O"
},
{
"id":108,
"orth":"guess",
"ner":"O"
},
{
"id":109,
"orth":"there",
"ner":"O"
},
{
"id":110,
"orth":"may",
"ner":"O"
},
{
"id":111,
"orth":"be",
"ner":"O"
},
{
"id":112,
"orth":"a",
"ner":"O"
},
{
"id":113,
"orth":"delay",
"ner":"O"
},
{
"id":114,
"orth":"until",
"ner":"O"
},
{
"id":115,
"orth":"a",
"ner":"O"
},
{
"id":116,
"orth":"reviewer",
"ner":"O"
},
{
"id":117,
"orth":"turns",
"ner":"O"
},
{
"id":118,
"orth":"up",
"ner":"O"
},
{
"id":119,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":120,
"orth":"It",
"ner":"O"
},
{
"id":121,
"orth":"'s",
"ner":"O"
},
{
"id":122,
"orth":"listed",
"ner":"O"
},
{
"id":123,
"orth":"in",
"ner":"O"
},
{
"id":124,
"orth":"the",
"ner":"O"
},
{
"id":125,
"orth":"relevant",
"ner":"O"
},
{
"id":126,
"orth":"form",
"ner":"O"
},
{
"id":127,
"orth":"eg",
"ner":"O"
},
{
"id":128,
"orth":"Wikipedia",
"ner":"O"
},
{
"id":129,
"orth":":",
"ner":"O"
},
{
"id":130,
"orth":"Good_article_nominations#Transport",
"ner":"O"
},
{
"id":131,
"orth":" ",
"ner":"O"
},
{
"id":132,
"orth":"\"",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":0
}
]
},
{
"raw":"You, sir, are my hero. Any chance you remember what page that's on?",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"You",
"ner":"O"
},
{
"id":1,
"orth":",",
"ner":"O"
},
{
"id":2,
"orth":"sir",
"ner":"O"
},
{
"id":3,
"orth":",",
"ner":"O"
},
{
"id":4,
"orth":"are",
"ner":"O"
},
{
"id":5,
"orth":"my",
"ner":"O"
},
{
"id":6,
"orth":"hero",
"ner":"O"
},
{
"id":7,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":8,
"orth":"Any",
"ner":"O"
},
{
"id":9,
"orth":"chance",
"ner":"O"
},
{
"id":10,
"orth":"you",
"ner":"O"
},
{
"id":11,
"orth":"remember",
"ner":"O"
},
{
"id":12,
"orth":"what",
"ner":"O"
},
{
"id":13,
"orth":"page",
"ner":"O"
},
{
"id":14,
"orth":"that",
"ner":"O"
},
{
"id":15,
"orth":"'s",
"ner":"O"
},
{
"id":16,
"orth":"on",
"ner":"O"
},
{
"id":17,
"orth":"?",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":0
}
]
},
{
"raw":"\"\n\nCongratulations from me as well, use the tools well. \u00a0\u00b7 talk \"",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"\"",
"ner":"O"
},
{
"id":1,
"orth":"\n\n",
"ner":"O"
},
{
"id":2,
"orth":"Congratulations",
"ner":"O"
},
{
"id":3,
"orth":"from",
"ner":"O"
},
{
"id":4,
"orth":"me",
"ner":"O"
},
{
"id":5,
"orth":"as",
"ner":"O"
},
{
"id":6,
"orth":"well",
"ner":"O"
},
{
"id":7,
"orth":",",
"ner":"O"
},
{
"id":8,
"orth":"use",
"ner":"O"
},
{
"id":9,
"orth":"the",
"ner":"O"
},
{
"id":10,
"orth":"tools",
"ner":"O"
},
{
"id":11,
"orth":"well",
"ner":"O"
},
{
"id":12,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":13,
"orth":"\u00a0",
"ner":"O"
},
{
"id":14,
"orth":"\u00b7",
"ner":"O"
},
{
"id":15,
"orth":"talk",
"ner":"O"
},
{
"id":16,
"orth":"\"",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":0
}
]
},
{
"raw":"Why can't you believe how fat Artie is? Did you see him on his recent appearence on the Tonight Show with Jay Leno? He looks absolutely AWFUL! If I had to put money on it, I'd say that Artie Lange is a can't miss candidate for the 2007 Dead pool! \n\n \nKindly keep your malicious fingers off of my above comment, . Everytime you remove it, I will repost it!!!",
"sentences":[
{
"tokens":[
{
"id":0,
"orth":"Why",
"ner":"O"
},
{
"id":1,
"orth":"ca",
"ner":"O"
},
{
"id":2,
"orth":"n't",
"ner":"O"
},
{
"id":3,
"orth":"you",
"ner":"O"
},
{
"id":4,
"orth":"believe",
"ner":"O"
},
{
"id":5,
"orth":"how",
"ner":"O"
},
{
"id":6,
"orth":"fat",
"ner":"O"
},
{
"id":7,
"orth":"Artie",
"ner":"O"
},
{
"id":8,
"orth":"is",
"ner":"O"
},
{
"id":9,
"orth":"?",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":10,
"orth":"Did",
"ner":"O"
},
{
"id":11,
"orth":"you",
"ner":"O"
},
{
"id":12,
"orth":"see",
"ner":"O"
},
{
"id":13,
"orth":"him",
"ner":"O"
},
{
"id":14,
"orth":"on",
"ner":"O"
},
{
"id":15,
"orth":"his",
"ner":"O"
},
{
"id":16,
"orth":"recent",
"ner":"O"
},
{
"id":17,
"orth":"appearence",
"ner":"O"
},
{
"id":18,
"orth":"on",
"ner":"O"
},
{
"id":19,
"orth":"the",
"ner":"O"
},
{
"id":20,
"orth":"Tonight",
"ner":"O"
},
{
"id":21,
"orth":"Show",
"ner":"O"
},
{
"id":22,
"orth":"with",
"ner":"O"
},
{
"id":23,
"orth":"Jay",
"ner":"O"
},
{
"id":24,
"orth":"Leno",
"ner":"O"
},
{
"id":25,
"orth":"?",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":26,
"orth":"He",
"ner":"O"
},
{
"id":27,
"orth":"looks",
"ner":"O"
},
{
"id":28,
"orth":"absolutely",
"ner":"O"
},
{
"id":29,
"orth":"AWFUL",
"ner":"O"
},
{
"id":30,
"orth":"!",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":31,
"orth":"If",
"ner":"O"
},
{
"id":32,
"orth":"I",
"ner":"O"
},
{
"id":33,
"orth":"had",
"ner":"O"
},
{
"id":34,
"orth":"to",
"ner":"O"
},
{
"id":35,
"orth":"put",
"ner":"O"
},
{
"id":36,
"orth":"money",
"ner":"O"
},
{
"id":37,
"orth":"on",
"ner":"O"
},
{
"id":38,
"orth":"it",
"ner":"O"
},
{
"id":39,
"orth":",",
"ner":"O"
},
{
"id":40,
"orth":"I",
"ner":"O"
},
{
"id":41,
"orth":"'d",
"ner":"O"
},
{
"id":42,
"orth":"say",
"ner":"O"
},
{
"id":43,
"orth":"that",
"ner":"O"
},
{
"id":44,
"orth":"Artie",
"ner":"O"
},
{
"id":45,
"orth":"Lange",
"ner":"O"
},
{
"id":46,
"orth":"is",
"ner":"O"
},
{
"id":47,
"orth":"a",
"ner":"O"
},
{
"id":48,
"orth":"ca",
"ner":"O"
},
{
"id":49,
"orth":"n't",
"ner":"O"
},
{
"id":50,
"orth":"miss",
"ner":"O"
},
{
"id":51,
"orth":"candidate",
"ner":"O"
},
{
"id":52,
"orth":"for",
"ner":"O"
},
{
"id":53,
"orth":"the",
"ner":"O"
},
{
"id":54,
"orth":"2007",
"ner":"O"
},
{
"id":55,
"orth":"Dead",
"ner":"O"
},
{
"id":56,
"orth":"pool",
"ner":"O"
},
{
"id":57,
"orth":"!",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":58,
"orth":" \n\n \n",
"ner":"O"
},
{
"id":59,
"orth":"Kindly",
"ner":"O"
},
{
"id":60,
"orth":"keep",
"ner":"O"
},
{
"id":61,
"orth":"your",
"ner":"O"
},
{
"id":62,
"orth":"malicious",
"ner":"O"
},
{
"id":63,
"orth":"fingers",
"ner":"O"
},
{
"id":64,
"orth":"off",
"ner":"O"
},
{
"id":65,
"orth":"of",
"ner":"O"
},
{
"id":66,
"orth":"my",
"ner":"O"
},
{
"id":67,
"orth":"above",
"ner":"O"
},
{
"id":68,
"orth":"comment",
"ner":"O"
},
{
"id":69,
"orth":",",
"ner":"O"
},
{
"id":70,
"orth":".",
"ner":"O"
}
],
"brackets":[
]
},
{
"tokens":[
{
"id":71,
"orth":"Everytime",
"ner":"O"
},
{
"id":72,
"orth":"you",
"ner":"O"
},
{
"id":73,
"orth":"remove",
"ner":"O"
},
{
"id":74,
"orth":"it",
"ner":"O"
},
{
"id":75,
"orth":",",
"ner":"O"
},
{
"id":76,
"orth":"I",
"ner":"O"
},
{
"id":77,
"orth":"will",
"ner":"O"
},
{
"id":78,
"orth":"repost",
"ner":"O"
},
{
"id":79,
"orth":"it",
"ner":"O"
},
{
"id":80,
"orth":"!",
"ner":"O"
},
{
"id":81,
"orth":"!",
"ner":"O"
},
{
"id":82,
"orth":"!",
"ner":"O"
}
],
"brackets":[
]
}
],
"cats":[
{
"label":"insult",
"value":0
},
{
"label":"obscene",
"value":0
},
{
"label":"severe_toxic",
"value":0
},
{
"label":"toxic",
"value":1
}
]
}
]
}
]
Reference in New Issue View Git Blame Copy Permalink