initial release

README.md

@@ -1,3 +1,39 @@
----
-license: cc-by-sa-4.0
----
+---
+language:
+- "en"
+tags:
+- "english"
+- "token-classification"
+- "pos"
+- "dependency-parsing"
+datasets:
+- "universal_dependencies"
+license: "cc-by-sa-4.0"
+pipeline_tag: "token-classification"
+---
+
+# roberta-base-english-upos
+
+## Model Description
+
+This is a RoBERTa model pre-trained with [UD_English-EWT](https://github.com/UniversalDependencies/UD_English-EWT) for POS-tagging and dependency-parsing, derived from [roberta-base](https://huggingface.co/roberta-base). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForTokenClassification
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-english-upos")
+model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-base-english-upos")
+```
+
+or
+
+```py
+import esupar
+nlp=esupar.load("KoichiYasuoka/roberta-base-english-upos")
+```
+
+## See Also
+
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa models
+

config.json

@@ -0,0 +1,1500 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADP+PRON",
+    "3": "ADV",
+    "4": "ADV+AUX",
+    "5": "ADV+PART",
+    "6": "AUX",
+    "7": "AUX+PART",
+    "8": "B-ADJ",
+    "9": "B-ADJ+ADJ",
+    "10": "B-ADJ+NOUN",
+    "11": "B-ADJ+NOUN+NOUN",
+    "12": "B-ADJ+PART",
+    "13": "B-ADJ+PROPN",
+    "14": "B-ADJ+PUNCT",
+    "15": "B-ADP",
+    "16": "B-ADP+NOUN",
+    "17": "B-ADV",
+    "18": "B-ADV+AUX",
+    "19": "B-ADV+PUNCT",
+    "20": "B-AUX",
+    "21": "B-AUX+PART",
+    "22": "B-AUX+PART+VERB",
+    "23": "B-AUX+VERB",
+    "24": "B-CCONJ",
+    "25": "B-DET",
+    "26": "B-DET+AUX",
+    "27": "B-DET+NOUN",
+    "28": "B-INTJ",
+    "29": "B-INTJ+PUNCT",
+    "30": "B-NOUN",
+    "31": "B-NOUN+AUX",
+    "32": "B-NOUN+NOUN",
+    "33": "B-NOUN+NOUN+VERB",
+    "34": "B-NOUN+PART",
+    "35": "B-NOUN+PUNCT",
+    "36": "B-NOUN+VERB",
+    "37": "B-NUM",
+    "38": "B-PART",
+    "39": "B-PRON",
+    "40": "B-PRON+ADJ",
+    "41": "B-PRON+ADV",
+    "42": "B-PRON+AUX",
+    "43": "B-PRON+PART",
+    "44": "B-PRON+VERB",
+    "45": "B-PROPN",
+    "46": "B-PROPN+PART",
+    "47": "B-PROPN+PROPN",
+    "48": "B-PROPN+PUNCT",
+    "49": "B-PUNCT",
+    "50": "B-PUNCT+PUNCT",
+    "51": "B-PUNCT+PUNCT+PUNCT",
+    "52": "B-SCONJ",
+    "53": "B-SYM",
+    "54": "B-VERB",
+    "55": "B-VERB+ADJ",
+    "56": "B-VERB+ADJ+CCONJ",
+    "57": "B-VERB+ADP",
+    "58": "B-VERB+ADV",
+    "59": "B-VERB+DET",
+    "60": "B-VERB+NOUN",
+    "61": "B-VERB+NOUN+NOUN",
+    "62": "B-VERB+PART",
+    "63": "B-VERB+PRON",
+    "64": "B-VERB+SCONJ",
+    "65": "B-X",
+    "66": "B-X+PUNCT",
+    "67": "B-X+X",
+    "68": "B-X+X+PRON",
+    "69": "CCONJ",
+    "70": "DET",
+    "71": "DET+NUM",
+    "72": "I-ADJ",
+    "73": "I-ADJ+ADJ",
+    "74": "I-ADJ+NOUN",
+    "75": "I-ADJ+NOUN+NOUN",
+    "76": "I-ADJ+PART",
+    "77": "I-ADJ+PROPN",
+    "78": "I-ADJ+PUNCT",
+    "79": "I-ADP",
+    "80": "I-ADP+NOUN",
+    "81": "I-ADV",
+    "82": "I-ADV+AUX",
+    "83": "I-ADV+PUNCT",
+    "84": "I-AUX",
+    "85": "I-AUX+PART",
+    "86": "I-AUX+PART+VERB",
+    "87": "I-AUX+VERB",
+    "88": "I-CCONJ",
+    "89": "I-DET",
+    "90": "I-DET+AUX",
+    "91": "I-DET+NOUN",
+    "92": "I-INTJ",
+    "93": "I-INTJ+PUNCT",
+    "94": "I-NOUN",
+    "95": "I-NOUN+AUX",
+    "96": "I-NOUN+NOUN",
+    "97": "I-NOUN+NOUN+VERB",
+    "98": "I-NOUN+PART",
+    "99": "I-NOUN+PUNCT",
+    "100": "I-NOUN+VERB",
+    "101": "I-NUM",
+    "102": "I-PART",
+    "103": "I-PRON",
+    "104": "I-PRON+ADJ",
+    "105": "I-PRON+ADV",
+    "106": "I-PRON+AUX",
+    "107": "I-PRON+PART",
+    "108": "I-PRON+VERB",
+    "109": "I-PROPN",
+    "110": "I-PROPN+PART",
+    "111": "I-PROPN+PROPN",
+    "112": "I-PROPN+PUNCT",
+    "113": "I-PUNCT",
+    "114": "I-PUNCT+PUNCT",
+    "115": "I-PUNCT+PUNCT+PUNCT",
+    "116": "I-SCONJ",
+    "117": "I-SYM",
+    "118": "I-VERB",
+    "119": "I-VERB+ADJ",
+    "120": "I-VERB+ADJ+CCONJ",
+    "121": "I-VERB+ADP",
+    "122": "I-VERB+ADV",
+    "123": "I-VERB+DET",
+    "124": "I-VERB+NOUN",
+    "125": "I-VERB+NOUN+NOUN",
+    "126": "I-VERB+PART",
+    "127": "I-VERB+PRON",
+    "128": "I-VERB+SCONJ",
+    "129": "I-X",
+    "130": "I-X+PUNCT",
+    "131": "I-X+X",
+    "132": "I-X+X+PRON",
+    "133": "INTJ",
+    "134": "NOUN",
+    "135": "NOUN+AUX",
+    "136": "NOUN+PART",
+    "137": "NUM",
+    "138": "PART",
+    "139": "PRON",
+    "140": "PRON+AUX",
+    "141": "PRON+VERB",
+    "142": "PROPN",
+    "143": "PROPN+PART",
+    "144": "PUNCT",
+    "145": "PUNCT+PUNCT",
+    "146": "PUNCT+PUNCT+PUNCT",
+    "147": "PUNCT+SYM",
+    "148": "SCONJ",
+    "149": "SYM",
+    "150": "SYM+PUNCT",
+    "151": "SYM+SYM",
+    "152": "VERB",
+    "153": "VERB+ADP",
+    "154": "VERB+PART",
+    "155": "VERB+PRON",
+    "156": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADP+PRON": 2,
+    "ADV": 3,
+    "ADV+AUX": 4,
+    "ADV+PART": 5,
+    "AUX": 6,
+    "AUX+PART": 7,
+    "B-ADJ": 8,
+    "B-ADJ+ADJ": 9,
+    "B-ADJ+NOUN": 10,
+    "B-ADJ+NOUN+NOUN": 11,
+    "B-ADJ+PART": 12,
+    "B-ADJ+PROPN": 13,
+    "B-ADJ+PUNCT": 14,
+    "B-ADP": 15,
+    "B-ADP+NOUN": 16,
+    "B-ADV": 17,
+    "B-ADV+AUX": 18,
+    "B-ADV+PUNCT": 19,
+    "B-AUX": 20,
+    "B-AUX+PART": 21,
+    "B-AUX+PART+VERB": 22,
+    "B-AUX+VERB": 23,
+    "B-CCONJ": 24,
+    "B-DET": 25,
+    "B-DET+AUX": 26,
+    "B-DET+NOUN": 27,
+    "B-INTJ": 28,
+    "B-INTJ+PUNCT": 29,
+    "B-NOUN": 30,
+    "B-NOUN+AUX": 31,
+    "B-NOUN+NOUN": 32,
+    "B-NOUN+NOUN+VERB": 33,
+    "B-NOUN+PART": 34,
+    "B-NOUN+PUNCT": 35,
+    "B-NOUN+VERB": 36,
+    "B-NUM": 37,
+    "B-PART": 38,
+    "B-PRON": 39,
+    "B-PRON+ADJ": 40,
+    "B-PRON+ADV": 41,
+    "B-PRON+AUX": 42,
+    "B-PRON+PART": 43,
+    "B-PRON+VERB": 44,
+    "B-PROPN": 45,
+    "B-PROPN+PART": 46,
+    "B-PROPN+PROPN": 47,
+    "B-PROPN+PUNCT": 48,
+    "B-PUNCT": 49,
+    "B-PUNCT+PUNCT": 50,
+    "B-PUNCT+PUNCT+PUNCT": 51,
+    "B-SCONJ": 52,
+    "B-SYM": 53,
+    "B-VERB": 54,
+    "B-VERB+ADJ": 55,
+    "B-VERB+ADJ+CCONJ": 56,
+    "B-VERB+ADP": 57,
+    "B-VERB+ADV": 58,
+    "B-VERB+DET": 59,
+    "B-VERB+NOUN": 60,
+    "B-VERB+NOUN+NOUN": 61,
+    "B-VERB+PART": 62,
+    "B-VERB+PRON": 63,
+    "B-VERB+SCONJ": 64,
+    "B-X": 65,
+    "B-X+PUNCT": 66,
+    "B-X+X": 67,
+    "B-X+X+PRON": 68,
+    "CCONJ": 69,
+    "DET": 70,
+    "DET+NUM": 71,
+    "I-ADJ": 72,
+    "I-ADJ+ADJ": 73,
+    "I-ADJ+NOUN": 74,
+    "I-ADJ+NOUN+NOUN": 75,
+    "I-ADJ+PART": 76,
+    "I-ADJ+PROPN": 77,
+    "I-ADJ+PUNCT": 78,
+    "I-ADP": 79,
+    "I-ADP+NOUN": 80,
+    "I-ADV": 81,
+    "I-ADV+AUX": 82,
+    "I-ADV+PUNCT": 83,
+    "I-AUX": 84,
+    "I-AUX+PART": 85,
+    "I-AUX+PART+VERB": 86,
+    "I-AUX+VERB": 87,
+    "I-CCONJ": 88,
+    "I-DET": 89,
+    "I-DET+AUX": 90,
+    "I-DET+NOUN": 91,
+    "I-INTJ": 92,
+    "I-INTJ+PUNCT": 93,
+    "I-NOUN": 94,
+    "I-NOUN+AUX": 95,
+    "I-NOUN+NOUN": 96,
+    "I-NOUN+NOUN+VERB": 97,
+    "I-NOUN+PART": 98,
+    "I-NOUN+PUNCT": 99,
+    "I-NOUN+VERB": 100,
+    "I-NUM": 101,
+    "I-PART": 102,
+    "I-PRON": 103,
+    "I-PRON+ADJ": 104,
+    "I-PRON+ADV": 105,
+    "I-PRON+AUX": 106,
+    "I-PRON+PART": 107,
+    "I-PRON+VERB": 108,
+    "I-PROPN": 109,
+    "I-PROPN+PART": 110,
+    "I-PROPN+PROPN": 111,
+    "I-PROPN+PUNCT": 112,
+    "I-PUNCT": 113,
+    "I-PUNCT+PUNCT": 114,
+    "I-PUNCT+PUNCT+PUNCT": 115,
+    "I-SCONJ": 116,
+    "I-SYM": 117,
+    "I-VERB": 118,
+    "I-VERB+ADJ": 119,
+    "I-VERB+ADJ+CCONJ": 120,
+    "I-VERB+ADP": 121,
+    "I-VERB+ADV": 122,
+    "I-VERB+DET": 123,
+    "I-VERB+NOUN": 124,
+    "I-VERB+NOUN+NOUN": 125,
+    "I-VERB+PART": 126,
+    "I-VERB+PRON": 127,
+    "I-VERB+SCONJ": 128,
+    "I-X": 129,
+    "I-X+PUNCT": 130,
+    "I-X+X": 131,
+    "I-X+X+PRON": 132,
+    "INTJ": 133,
+    "NOUN": 134,
+    "NOUN+AUX": 135,
+    "NOUN+PART": 136,
+    "NUM": 137,
+    "PART": 138,
+    "PRON": 139,
+    "PRON+AUX": 140,
+    "PRON+VERB": 141,
+    "PROPN": 142,
+    "PROPN+PART": 143,
+    "PUNCT": 144,
+    "PUNCT+PUNCT": 145,
+    "PUNCT+PUNCT+PUNCT": 146,
+    "PUNCT+SYM": 147,
+    "SCONJ": 148,
+    "SYM": 149,
+    "SYM+PUNCT": 150,
+    "SYM+SYM": 151,
+    "VERB": 152,
+    "VERB+ADP": 153,
+    "VERB+PART": 154,
+    "VERB+PRON": 155,
+    "X": 156
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "task_specific_params": {
+    "upos_multiword": {
+      "ADJ+ADJ": {
+        "bigenough": [
+          "big",
+          "enough"
+        ],
+        "interestingsocial": [
+          "interesting",
+          "social"
+        ]
+      },
+      "ADJ+NOUN": {
+        "bigsource": [
+          "big",
+          "source"
+        ],
+        "distractingelements": [
+          "distracting",
+          "elements"
+        ],
+        "gruelingsanctions": [
+          "grueling",
+          "sanctions"
+        ],
+        "longexposures": [
+          "long",
+          "exposures"
+        ],
+        "longhair": [
+          "long",
+          "hair"
+        ],
+        "ongoingsummaries": [
+          "ongoing",
+          "summaries"
+        ],
+        "pre-meetingsite": [
+          "pre-meeting",
+          "site"
+        ],
+        "stronghints": [
+          "strong",
+          "hints"
+        ]
+      },
+      "ADJ+PART": {
+        "elses": [
+          "else",
+          "s"
+        ]
+      },
+      "ADJ+PROPN": {
+        "Nationwidetints": [
+          "Nationwide",
+          "tints"
+        ]
+      },
+      "ADJ+PUNCT": {
+        "e.g.:": [
+          "e.g.",
+          ":"
+        ],
+        "i.e.,": [
+          "i.e.",
+          ","
+        ]
+      },
+      "ADP+NOUN": {
+        "Infact": [
+          "In",
+          "fact"
+        ],
+        "overtime": [
+          "over",
+          "time"
+        ]
+      },
+      "ADP+PRON": {
+        "init": [
+          "in",
+          "it"
+        ]
+      },
+      "ADV+AUX": {
+        "Heres": [
+          "Here",
+          "s"
+        ]
+      },
+      "ADV+PART": {
+        "into": [
+          "in",
+          "to"
+        ]
+      },
+      "ADV+PUNCT": {
+        "E.g.,": [
+          "E.g.",
+          ","
+        ],
+        "i.e.,": [
+          "i.e.",
+          ","
+        ],
+        "i.e.:": [
+          "i.e.",
+          ":"
+        ]
+      },
+      "AUX+PART": {
+        "Aren't": [
+          "Are",
+          "n't"
+        ],
+        "CANT": [
+          "CA",
+          "NT"
+        ],
+        "Can't": [
+          "Ca",
+          "n't"
+        ],
+        "Cannot": [
+          "Can",
+          "not"
+        ],
+        "DON'T": [
+          "DO",
+          "N'T"
+        ],
+        "DONT": [
+          "DO",
+          "NT"
+        ],
+        "Don't": [
+          "Do",
+          "n't"
+        ],
+        "Dont": [
+          "Do",
+          "nt"
+        ],
+        "Haven't": [
+          "Have",
+          "n't"
+        ],
+        "ain't": [
+          "ai",
+          "n't"
+        ],
+        "aint": [
+          "ai",
+          "nt"
+        ],
+        "aren't": [
+          "are",
+          "n't"
+        ],
+        "arent": [
+          "are",
+          "nt"
+        ],
+        "can't": [
+          "ca",
+          "n't"
+        ],
+        "cannot": [
+          "can",
+          "not"
+        ],
+        "cant": [
+          "ca",
+          "nt"
+        ],
+        "can\u2019t": [
+          "ca",
+          "n\u2019t"
+        ],
+        "didn't": [
+          "did",
+          "n't"
+        ],
+        "didn\u2019t": [
+          "did",
+          "n\u2019t"
+        ],
+        "doesn't": [
+          "does",
+          "n't"
+        ],
+        "don't": [
+          "do",
+          "n't"
+        ],
+        "dont": [
+          "do",
+          "nt"
+        ],
+        "don\u2019t": [
+          "do",
+          "n\u2019t"
+        ],
+        "haven't": [
+          "have",
+          "n't"
+        ],
+        "wasent": [
+          "wase",
+          "nt"
+        ],
+        "weren't": [
+          "were",
+          "n't"
+        ],
+        "weren\u2019t": [
+          "were",
+          "n\u2019t"
+        ],
+        "won't": [
+          "wo",
+          "n't"
+        ],
+        "wont": [
+          "wo",
+          "nt"
+        ],
+        "won\u2019t": [
+          "wo",
+          "n\u2019t"
+        ]
+      },
+      "AUX+PART+VERB": {
+        "dunno": [
+          "du",
+          "n",
+          "no"
+        ]
+      },
+      "AUX+VERB": {
+        "beingsaid": [
+          "being",
+          "said"
+        ],
+        "beingsent": [
+          "being",
+          "sent"
+        ],
+        "beingshipped": [
+          "being",
+          "shipped"
+        ],
+        "beingspoken": [
+          "being",
+          "spoken"
+        ],
+        "havingsaid": [
+          "having",
+          "said"
+        ]
+      },
+      "DET+AUX": {
+        "thes": [
+          "the",
+          "s"
+        ]
+      },
+      "DET+NOUN": {
+        "ALOT": [
+          "A",
+          "LOT"
+        ],
+        "Alot": [
+          "A",
+          "lot"
+        ],
+        "apart": [
+          "a",
+          "part"
+        ],
+        "awhile": [
+          "a",
+          "while"
+        ],
+        "sometime": [
+          "some",
+          "time"
+        ]
+      },
+      "DET+NUM": {
+        "everyone": [
+          "every",
+          "one"
+        ]
+      },
+      "INTJ+PUNCT": {
+        "ta',": [
+          "ta'",
+          ","
+        ]
+      },
+      "NOUN+AUX": {
+        "breathingshould": [
+          "breathing",
+          "should"
+        ],
+        "doghas": [
+          "dog",
+          "has"
+        ]
+      },
+      "NOUN+NOUN": {
+        "Drivingschool": [
+          "Driving",
+          "school"
+        ],
+        "counselingservices": [
+          "counseling",
+          "services"
+        ],
+        "datingservice": [
+          "dating",
+          "service"
+        ],
+        "doghouse": [
+          "dog",
+          "house"
+        ],
+        "drivingschool": [
+          "driving",
+          "school"
+        ],
+        "engineeringservices": [
+          "engineering",
+          "services"
+        ],
+        "kingsnake": [
+          "king",
+          "snake"
+        ],
+        "kingsnakes": [
+          "king",
+          "snakes"
+        ],
+        "lightingshowroom": [
+          "lighting",
+          "showroom"
+        ],
+        "mpgnumber": [
+          "mpg",
+          "number"
+        ],
+        "testingschedule": [
+          "testing",
+          "schedule"
+        ],
+        "towingservices": [
+          "towing",
+          "services"
+        ]
+      },
+      "NOUN+NOUN+VERB": {
+        "RecruitingMeetingscheduled": [
+          "Recruiting",
+          "Meeting",
+          "scheduled"
+        ]
+      },
+      "NOUN+PART": {
+        "DAUGHTERS": [
+          "DAUGHTER",
+          "S"
+        ],
+        "Kids": [
+          "Kid",
+          "s"
+        ],
+        "Mares": [
+          "Mare",
+          "s"
+        ],
+        "Smokers": [
+          "Smoker",
+          "s"
+        ],
+        "Travelers": [
+          "Traveler",
+          "s"
+        ],
+        "animals": [
+          "animal",
+          "s"
+        ],
+        "bachelors": [
+          "bachelor",
+          "s"
+        ],
+        "bakers": [
+          "baker",
+          "s"
+        ],
+        "beginners": [
+          "beginner",
+          "s"
+        ],
+        "bettas": [
+          "betta",
+          "s"
+        ],
+        "boys": [
+          "boy",
+          "s"
+        ],
+        "cars": [
+          "car",
+          "s"
+        ],
+        "cats": [
+          "cat",
+          "s"
+        ],
+        "dads": [
+          "dad",
+          "s"
+        ],
+        "doctors": [
+          "doctor",
+          "s"
+        ],
+        "dogs": [
+          "dog",
+          "s"
+        ],
+        "drivers": [
+          "driver",
+          "s"
+        ],
+        "friends": [
+          "friend",
+          "s"
+        ],
+        "grandmas": [
+          "grandma",
+          "s"
+        ],
+        "horses": [
+          "horse",
+          "s"
+        ],
+        "humans": [
+          "human",
+          "s"
+        ],
+        "males": [
+          "male",
+          "s"
+        ],
+        "manufacturers": [
+          "manufacturer",
+          "s"
+        ],
+        "mares": [
+          "mare",
+          "s"
+        ],
+        "nights": [
+          "night",
+          "s"
+        ],
+        "owners": [
+          "owner",
+          "s"
+        ],
+        "peoples": [
+          "people",
+          "s"
+        ],
+        "persons": [
+          "person",
+          "s"
+        ],
+        "scammers": [
+          "scammer",
+          "s"
+        ],
+        "sons": [
+          "son",
+          "s"
+        ],
+        "teams": [
+          "team",
+          "s"
+        ],
+        "todays": [
+          "today",
+          "s"
+        ],
+        "trainers": [
+          "trainer",
+          "s"
+        ],
+        "visitors": [
+          "visitor",
+          "s"
+        ],
+        "wits": [
+          "wit",
+          "s"
+        ],
+        "workers": [
+          "worker",
+          "s"
+        ]
+      },
+      "NOUN+PUNCT": {
+        "Fax.(": [
+          "Fax.",
+          "("
+        ],
+        "a.m.,": [
+          "a.m.",
+          ","
+        ],
+        "lb.,": [
+          "lb.",
+          ","
+        ],
+        "mins.,": [
+          "mins.",
+          ","
+        ],
+        "oz.,": [
+          "oz.",
+          ","
+        ],
+        "p.m.,": [
+          "p.m.",
+          ","
+        ]
+      },
+      "NOUN+VERB": {
+        "thingsounded": [
+          "thing",
+          "sounded"
+        ]
+      },
+      "PRON+ADJ": {
+        "everythingset": [
+          "everything",
+          "set"
+        ],
+        "somethingsuch": [
+          "something",
+          "such"
+        ]
+      },
+      "PRON+ADV": {
+        "somethingsometime": [
+          "something",
+          "sometime"
+        ]
+      },
+      "PRON+AUX": {
+        "ITS": [
+          "IT",
+          "S"
+        ],
+        "Im": [
+          "I",
+          "m"
+        ],
+        "Its": [
+          "It",
+          "s"
+        ],
+        "Whats": [
+          "What",
+          "s"
+        ],
+        "Your": [
+          "You",
+          "r"
+        ],
+        "hes": [
+          "he",
+          "s"
+        ],
+        "id": [
+          "i",
+          "d"
+        ],
+        "im": [
+          "i",
+          "m"
+        ],
+        "its": [
+          "it",
+          "s"
+        ],
+        "iv": [
+          "i",
+          "v"
+        ],
+        "ive": [
+          "i",
+          "ve"
+        ],
+        "thats": [
+          "that",
+          "s"
+        ],
+        "their": [
+          "thei",
+          "r"
+        ],
+        "there": [
+          "the",
+          "re"
+        ],
+        "ur": [
+          "u",
+          "r"
+        ],
+        "your": [
+          "you",
+          "r"
+        ]
+      },
+      "PRON+PART": {
+        "anyones": [
+          "anyone",
+          "s"
+        ]
+      },
+      "PRON+VERB": {
+        "Thats": [
+          "That",
+          "s"
+        ],
+        "Theres": [
+          "There",
+          "s"
+        ],
+        "everythingset": [
+          "everything",
+          "set"
+        ],
+        "iguz": [
+          "i",
+          "guz"
+        ],
+        "im": [
+          "i",
+          "m"
+        ],
+        "its": [
+          "it",
+          "s"
+        ],
+        "theres": [
+          "there",
+          "s"
+        ],
+        "youthank": [
+          "you",
+          "thank"
+        ]
+      },
+      "PROPN+PART": {
+        "BJs": [
+          "BJ",
+          "s"
+        ],
+        "Chilis": [
+          "Chili",
+          "s"
+        ],
+        "Friscos": [
+          "Frisco",
+          "s"
+        ],
+        "Hams": [
+          "Ham",
+          "s"
+        ],
+        "Kobeys": [
+          "Kobey",
+          "s"
+        ],
+        "LWs": [
+          "LW",
+          "s"
+        ],
+        "Leonardos": [
+          "Leonardo",
+          "s"
+        ],
+        "Mortons": [
+          "Morton",
+          "s"
+        ],
+        "Travellers": [
+          "Traveller",
+          "s"
+        ],
+        "Valentines": [
+          "Valentine",
+          "s"
+        ],
+        "Years": [
+          "Year",
+          "s"
+        ],
+        "jacks": [
+          "jack",
+          "s"
+        ]
+      },
+      "PROPN+PROPN": {
+        "G&GAutomotive": [
+          "G&G",
+          "Automotive"
+        ],
+        "drivingschool": [
+          "driving",
+          "school"
+        ]
+      },
+      "PROPN+PUNCT": {
+        "B.,": [
+          "B.",
+          ","
+        ],
+        "D.C.,": [
+          "D.C.",
+          ","
+        ],
+        "Inc.\"": [
+          "Inc.",
+          "\""
+        ],
+        "M.,": [
+          "M.",
+          ","
+        ],
+        "N.O.?": [
+          "N.O.",
+          "?"
+        ],
+        "Que.,": [
+          "Que.",
+          ","
+        ],
+        "U.N.,": [
+          "U.N.",
+          ","
+        ],
+        "U.S.)": [
+          "U.S.",
+          ")"
+        ],
+        "U.S.-": [
+          "U.S.",
+          "-"
+        ],
+        "Va.-": [
+          "Va.",
+          "-"
+        ]
+      },
+      "PUNCT+PUNCT": {
+        "!\"": [
+          "!",
+          "\""
+        ],
+        "!)": [
+          "!",
+          ")"
+        ],
+        "\"(": [
+          "\"",
+          "("
+        ],
+        "\")": [
+          "\"",
+          ")"
+        ],
+        "\",": [
+          "\"",
+          ","
+        ],
+        "\"-": [
+          "\"",
+          "-"
+        ],
+        "\"...": [
+          "\"",
+          "..."
+        ],
+        "\":": [
+          "\"",
+          ":"
+        ],
+        "')": [
+          "'",
+          ")"
+        ],
+        "',": [
+          "'",
+          ","
+        ],
+        "(\"": [
+          "(",
+          "\""
+        ],
+        "(\"\"": [
+          "(",
+          "\"\""
+        ],
+        ")\"": [
+          ")",
+          "\""
+        ],
+        ")(": [
+          ")",
+          "("
+        ],
+        "),": [
+          ")",
+          ","
+        ],
+        ").": [
+          ")",
+          "."
+        ],
+        ")...": [
+          ")",
+          "..."
+        ],
+        "):": [
+          ")",
+          ":"
+        ],
+        ");": [
+          ")",
+          ";"
+        ],
+        "*,": [
+          "*",
+          ","
+        ],
+        ",\"": [
+          ",",
+          "\""
+        ],
+        ",'": [
+          ",",
+          "'"
+        ],
+        ",''": [
+          ",",
+          "''"
+        ],
+        ",...": [
+          ",",
+          "..."
+        ],
+        "-\"": [
+          "-",
+          "\""
+        ],
+        ".'": [
+          ".",
+          "'"
+        ],
+        "...\"": [
+          "...",
+          "\""
+        ],
+        "?\"": [
+          "?",
+          "\""
+        ],
+        "?)": [
+          "?",
+          ")"
+        ],
+        "?]": [
+          "?",
+          "]"
+        ],
+        "],": [
+          "]",
+          ","
+        ]
+      },
+      "PUNCT+PUNCT+PUNCT": {
+        "!),": [
+          "!",
+          ")",
+          ","
+        ],
+        "\"),": [
+          "\"",
+          ")",
+          ","
+        ],
+        "?),": [
+          "?",
+          ")",
+          ","
+        ]
+      },
+      "PUNCT+SYM": {
+        "($": [
+          "(",
+          "$"
+        ]
+      },
+      "SYM+PUNCT": {
+        "$,": [
+          "$",
+          ","
+        ],
+        "%)": [
+          "%",
+          ")"
+        ],
+        "-'": [
+          "-",
+          "'"
+        ]
+      },
+      "SYM+SYM": {
+        "-$": [
+          "-",
+          "$"
+        ]
+      },
+      "VERB+ADJ": {
+        "doingshoddy": [
+          "doing",
+          "shoddy"
+        ],
+        "facingserious": [
+          "facing",
+          "serious"
+        ],
+        "outsourcingspecial": [
+          "outsourcing",
+          "special"
+        ],
+        "reinforcingsimilar": [
+          "reinforcing",
+          "similar"
+        ]
+      },
+      "VERB+ADJ+CCONJ": {
+        "lookingsmugand": [
+          "looking",
+          "smug",
+          "and"
+        ]
+      },
+      "VERB+ADP": {
+        "Login": [
+          "Log",
+          "in"
+        ],
+        "gamingsince": [
+          "gaming",
+          "since"
+        ],
+        "goto": [
+          "go",
+          "to"
+        ],
+        "hummingsince": [
+          "humming",
+          "since"
+        ],
+        "investigatingsince": [
+          "investigating",
+          "since"
+        ],
+        "setup": [
+          "set",
+          "up"
+        ]
+      },
+      "VERB+ADV": {
+        "totalingsomewhere": [
+          "totaling",
+          "somewhere"
+        ]
+      },
+      "VERB+DET": {
+        "discussingsome": [
+          "discussing",
+          "some"
+        ],
+        "doingevery": [
+          "doing",
+          "every"
+        ],
+        "doingsome": [
+          "doing",
+          "some"
+        ],
+        "dumpingsome": [
+          "dumping",
+          "some"
+        ],
+        "experiencingsome": [
+          "experiencing",
+          "some"
+        ],
+        "meetingeach": [
+          "meeting",
+          "each"
+        ],
+        "readingsome": [
+          "reading",
+          "some"
+        ],
+        "regardingsome": [
+          "regarding",
+          "some"
+        ],
+        "replacingsome": [
+          "replacing",
+          "some"
+        ]
+      },
+      "VERB+NOUN": {
+        "doingscissors": [
+          "doing",
+          "scissors"
+        ],
+        "followingsuggestion": [
+          "following",
+          "suggestion"
+        ],
+        "formingeggs": [
+          "forming",
+          "eggs"
+        ],
+        "meaningshell": [
+          "meaning",
+          "shell"
+        ],
+        "playingsports": [
+          "playing",
+          "sports"
+        ],
+        "producingshrubs": [
+          "producing",
+          "shrubs"
+        ],
+        "providingservices": [
+          "providing",
+          "services"
+        ],
+        "quittingsmoking": [
+          "quitting",
+          "smoking"
+        ]
+      },
+      "VERB+PART": {
+        "Gotta": [
+          "Got",
+          "ta"
+        ],
+        "aren't": [
+          "are",
+          "n't"
+        ],
+        "doesn't": [
+          "does",
+          "n't"
+        ],
+        "don't": [
+          "do",
+          "n't"
+        ],
+        "gonna": [
+          "gon",
+          "na"
+        ],
+        "gotta": [
+          "got",
+          "ta"
+        ],
+        "wana": [
+          "wan",
+          "a"
+        ],
+        "wanna": [
+          "wan",
+          "na"
+        ]
+      },
+      "VERB+PRON": {
+        "Lets": [
+          "Let",
+          "s"
+        ],
+        "callyou": [
+          "call",
+          "you"
+        ],
+        "doingeverything": [
+          "doing",
+          "everything"
+        ],
+        "lets": [
+          "let",
+          "s"
+        ]
+      },
+      "VERB+SCONJ": {
+        "decidewhether": [
+          "decide",
+          "whether"
+        ]
+      },
+      "X+PUNCT": {
+        "etc.)": [
+          "etc.",
+          ")"
+        ],
+        "etc.,": [
+          "etc.",
+          ","
+        ],
+        "etc..": [
+          "etc.",
+          "."
+        ]
+      },
+      "X+X": {
+        ").doc": [
+          ")",
+          ".doc"
+        ]
+      },
+      "X+X+PRON": {
+        "http://i.imgur.com/T2zff.jpghttp://i.imgur.com/Xytex.jpgI": [
+          "http://i.imgur.com/T2zff.jpg",
+          "http://i.imgur.com/Xytex.jpg",
+          "I"
+        ]
+      }
+    }
+  },
+  "tokenizer_class": "RobertaTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad92b564b4a62c21032ff9e63d6e0822f95d94fe8e028707dd480f7cce0bc15
+size 496790863

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

supar.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5166b493ed67370b1ee21ce283c31e3b145d34723e84fdb612a77e3665f0e53b
+size 549334503

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "tokenizer_class": "RobertaTokenizerFast"}