Added SEM tagging model

config.json

@@ -0,0 +1,164 @@
+{
+ "_name_or_path": "bert-base-cased",
+ "architectures": [
+ "BertForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "O",
+ "1": "ALT",
+ "2": "AND",
+ "3": "APP",
+ "4": "ART",
+ "5": "BUT",
+ "6": "COM",
+ "7": "CON",
+ "8": "COO",
+ "9": "DEC",
+ "10": "DEF",
+ "11": "DIS",
+ "12": "DOM",
+ "13": "DOW",
+ "14": "DST",
+ "15": "EFS",
+ "16": "EMP",
+ "17": "ENG",
+ "18": "ENS",
+ "19": "ENT",
+ "20": "EPG",
+ "21": "EPS",
+ "22": "EPT",
+ "23": "EQA",
+ "24": "ETG",
+ "25": "ETV",
+ "26": "EXC",
+ "27": "EXG",
+ "28": "EXN",
+ "29": "EXS",
+ "30": "EXT",
+ "31": "EXV",
+ "32": "FUT",
+ "33": "GPE",
+ "34": "HAP",
+ "35": "HAS",
+ "36": "IMP",
+ "37": "INT",
+ "38": "IST",
+ "39": "ITJ",
+ "40": "LES",
+ "41": "LOC",
+ "42": "MOR",
+ "43": "MOY",
+ "44": "NAT",
+ "45": "NEC",
+ "46": "NIL",
+ "47": "NOT",
+ "48": "NOW",
+ "49": "ORG",
+ "50": "PER",
+ "51": "POS",
+ "52": "PRO",
+ "53": "PRX",
+ "54": "PST",
+ "55": "QUA",
+ "56": "QUE",
+ "57": "REF",
+ "58": "REL",
+ "59": "RLI",
+ "60": "ROL",
+ "61": "SCO",
+ "62": "SUB",
+ "63": "TIM",
+ "64": "TOP",
+ "65": "UNK",
+ "66": "UOM",
+ "67": "YOC"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "ALT": 1,
+ "AND": 2,
+ "APP": 3,
+ "ART": 4,
+ "BUT": 5,
+ "COM": 6,
+ "CON": 7,
+ "COO": 8,
+ "DEC": 9,
+ "DEF": 10,
+ "DIS": 11,
+ "DOM": 12,
+ "DOW": 13,
+ "DST": 14,
+ "EFS": 15,
+ "EMP": 16,
+ "ENG": 17,
+ "ENS": 18,
+ "ENT": 19,
+ "EPG": 20,
+ "EPS": 21,
+ "EPT": 22,
+ "EQA": 23,
+ "ETG": 24,
+ "ETV": 25,
+ "EXC": 26,
+ "EXG": 27,
+ "EXN": 28,
+ "EXS": 29,
+ "EXT": 30,
+ "EXV": 31,
+ "FUT": 32,
+ "GPE": 33,
+ "HAP": 34,
+ "HAS": 35,
+ "IMP": 36,
+ "INT": 37,
+ "IST": 38,
+ "ITJ": 39,
+ "LES": 40,
+ "LOC": 41,
+ "MOR": 42,
+ "MOY": 43,
+ "NAT": 44,
+ "NEC": 45,
+ "NIL": 46,
+ "NOT": 47,
+ "NOW": 48,
+ "O": 0,
+ "ORG": 49,
+ "PER": 50,
+ "POS": 51,
+ "PRO": 52,
+ "PRX": 53,
+ "PST": 54,
+ "QUA": 55,
+ "QUE": 56,
+ "REF": 57,
+ "REL": 58,
+ "RLI": 59,
+ "ROL": 60,
+ "SCO": 61,
+ "SUB": 62,
+ "TIM": 63,
+ "TOP": 64,
+ "UNK": 65,
+ "UOM": 66,
+ "YOC": 67
+ },
+ "layer_norm_eps": 1e-12,
+ "max_position_embeddings": 512,
+ "model_type": "bert",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 0,
+ "position_embedding_type": "absolute",
+ "transformers_version": "4.6.1",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0afd0172c4f3c2f3e62175692650d17d9bdec7a5eab69f425002c40828e2b554
+size 431176439

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25332388fc0bf4165ddcd5fe3194f033c51640377f5d8a043cea8082237ddc19
+size 2415