initial release

README.md

@@ -0,0 +1,45 @@
+---
+language:
+- "ko"
+tags:
+- "korean"
+- "token-classification"
+- "pos"
+- "dependency-parsing"
+datasets:
+- "universal_dependencies"
+license: "apache-2.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "홍시 맛이 나서 홍시라 생각한다."
+- text: "紅柹 맛이 나서 紅柹라 生覺한다."
+---
+
+# deberta-base-korean-upos
+
+## Model Description
+
+This is a RoBERTa model pre-trained on Korean texts for POS-tagging and dependency-parsing, derived from [deberta-v3-base-korean](https://huggingface.co/team-lucid/deberta-v3-base-korean). Every word (어절) is tagged by [UPOS](https://universaldependencies.org/u/pos/)(Universal Part-Of-Speech).
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForTokenClassification,TokenClassificationPipeline
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-korean-upos")
+model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/deberta-base-korean-upos")
+pipeline=TokenClassificationPipeline(tokenizer=tokenizer,model=model,aggregation_strategy="simple")
+nlp=lambda x:[(x[t["start"]:t["end"]],t["entity_group"]) for t in pipeline(x)]
+print(nlp("홍시 맛이 나서 홍시라 생각한다."))
+```
+
+or
+
+```py
+import esupar
+nlp=esupar.load("KoichiYasuoka/deberta-base-korean-upos")
+print(nlp("홍시 맛이 나서 홍시라 생각한다."))
+```
+
+## See Also
+
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models

config.json

@@ -0,0 +1,153 @@
+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "B-ADJ",
+    "5": "B-ADP",
+    "6": "B-ADV",
+    "7": "B-AUX",
+    "8": "B-CCONJ",
+    "9": "B-DET",
+    "10": "B-INTJ",
+    "11": "B-NOUN",
+    "12": "B-NUM",
+    "13": "B-PART",
+    "14": "B-PRON",
+    "15": "B-PROPN",
+    "16": "B-PUNCT",
+    "17": "B-SCONJ",
+    "18": "B-SYM",
+    "19": "B-VERB",
+    "20": "B-X",
+    "21": "CCONJ",
+    "22": "DET",
+    "23": "I-ADJ",
+    "24": "I-ADP",
+    "25": "I-ADV",
+    "26": "I-AUX",
+    "27": "I-CCONJ",
+    "28": "I-DET",
+    "29": "I-INTJ",
+    "30": "I-NOUN",
+    "31": "I-NUM",
+    "32": "I-PART",
+    "33": "I-PRON",
+    "34": "I-PROPN",
+    "35": "I-PUNCT",
+    "36": "I-SCONJ",
+    "37": "I-SYM",
+    "38": "I-VERB",
+    "39": "I-X",
+    "40": "INTJ",
+    "41": "NOUN",
+    "42": "NUM",
+    "43": "NUM+PUNCT",
+    "44": "PART",
+    "45": "PRON",
+    "46": "PROPN",
+    "47": "PUNCT",
+    "48": "SCONJ",
+    "49": "SYM",
+    "50": "VERB",
+    "51": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "B-ADJ": 4,
+    "B-ADP": 5,
+    "B-ADV": 6,
+    "B-AUX": 7,
+    "B-CCONJ": 8,
+    "B-DET": 9,
+    "B-INTJ": 10,
+    "B-NOUN": 11,
+    "B-NUM": 12,
+    "B-PART": 13,
+    "B-PRON": 14,
+    "B-PROPN": 15,
+    "B-PUNCT": 16,
+    "B-SCONJ": 17,
+    "B-SYM": 18,
+    "B-VERB": 19,
+    "B-X": 20,
+    "CCONJ": 21,
+    "DET": 22,
+    "I-ADJ": 23,
+    "I-ADP": 24,
+    "I-ADV": 25,
+    "I-AUX": 26,
+    "I-CCONJ": 27,
+    "I-DET": 28,
+    "I-INTJ": 29,
+    "I-NOUN": 30,
+    "I-NUM": 31,
+    "I-PART": 32,
+    "I-PRON": 33,
+    "I-PROPN": 34,
+    "I-PUNCT": 35,
+    "I-SCONJ": 36,
+    "I-SYM": 37,
+    "I-VERB": 38,
+    "I-X": 39,
+    "INTJ": 40,
+    "NOUN": 41,
+    "NUM": 42,
+    "NUM+PUNCT": 43,
+    "PART": 44,
+    "PRON": 45,
+    "PROPN": 46,
+    "PUNCT": 47,
+    "SCONJ": 48,
+    "SYM": 49,
+    "VERB": 50,
+    "X": 51
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "task_specific_params": {
+    "upos_multiword": {
+      "NUM+PUNCT": {
+        "515": [
+          "5",
+          "15"
+        ]
+      }
+    }
+  },
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 0,
+  "vocab_size": 64100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5713197a0c2693b64f4a626e59ff6ff3cd35afbfa15ea443fb88c7220d79c5
+size 538945393

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

supar.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b9ee4ad4d19cce25befb5dfe309d301e2b9673bfdffcb0f20b3238960daa75
+size 600467177

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "unk_token": "[UNK]"
+}