Upload 7 files

README.md

@@ -1,3 +1,48 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- elenanereiss/german-ler
+language:
+- de
+base_model:
+- google-bert/bert-base-german-cased
+pipeline_tag: token-classification
+library_name: transformers
+---
+
+## German BERT for Legal NER
+
+**F1-Score:** **`99.762`**
+
+This model is fine-tuned on the [German LER dataset](https://huggingface.co/datasets/elenanereiss/german-ler), introduced in [this paper](https://link.springer.com/content/pdf/10.1007/978-3-030-33220-4_20.pdf). The LER dataset provides annotations across 19 fine-grained legal entity classes, capturing the complexity of legal texts in German.
+
+## Class-wise Performance Metrics
+
+The table below summarizes the class-wise performance metrics of our improved model:
+| Abbreviation | Class               | Dataset % | F1-Score |
+|--------------|---------------------|-----------|----------|
+| PER          | Person              | 3.26      | 94.47    |
+| RR           | Judge               | 2.83      | 99.56    |
+| AN           | Lawyer              | 0.21      | 92.31    |
+| LD           | Country             | 2.66      | 96.30    |
+| ST           | City                | 1.31      | 91.53    |
+| STR          | Street              | 0.25      | 95.05    |
+| LDS          | Landscape           | 0.37      | 88.24    |
+| ORG          | Organization        | 2.17      | 93.72    |
+| UN           | Company             | 1.97      | 98.16    |
+| INN          | Institution         | 4.09      | 97.73    |
+| GRT          | Court               | 5.99      | 98.32    |
+| MRK          | Brand               | 0.53      | 98.65    |
+| GS           | Law                 | 34.53     | 99.46    |
+| VO           | Ordinance           | 1.49      | 95.72    |
+| EUN          | European legal norm | 2.79      | 97.79    |
+| VS           | Regulation          | 1.13      | 89.73    |
+| VT           | Contract            | 5.34      | 99.22    |
+| RS           | Court decision      | 23.46     | 99.76    |
+| LIT          | Legal literature    | 5.60      | 98.09    |
+
+## Comparison of F1 Scores
+
+Below is a comparison of F1 scores between our previous model, [gbert-legal-ner](https://huggingface.co/PaDaS-Lab/gbert-legal-ner), and JuraNER:
+
+![f1-comparison](https://huggingface.co/harshildarji/JuraNER/resolve/main/f1.png)

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "bert-base-german-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "I-INN",
+    "1": "I-GRT",
+    "2": "I-RS",
+    "3": "B-ORG",
+    "4": "I-UN",
+    "5": "I-LDS",
+    "6": "I-GS",
+    "7": "I-LD",
+    "8": "I-ORG",
+    "9": "B-LD",
+    "10": "I-EUN",
+    "11": "B-INN",
+    "12": "I-VO",
+    "13": "B-GS",
+    "14": "B-AN",
+    "15": "I-RR",
+    "16": "I-AN",
+    "17": "B-UN",
+    "18": "B-RR",
+    "19": "I-STR",
+    "20": "B-PER",
+    "21": "I-VT",
+    "22": "I-MRK",
+    "23": "B-RS",
+    "24": "I-LIT",
+    "25": "B-VT",
+    "26": "B-STR",
+    "27": "B-VS",
+    "28": "B-VO",
+    "29": "B-EUN",
+    "30": "I-VS",
+    "31": "B-ST",
+    "32": "I-ST",
+    "33": "B-LIT",
+    "34": "O",
+    "35": "B-LDS",
+    "36": "B-GRT",
+    "37": "B-MRK",
+    "38": "I-PER",
+    "39": "PAD"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AN": 14,
+    "B-EUN": 29,
+    "B-GRT": 36,
+    "B-GS": 13,
+    "B-INN": 11,
+    "B-LD": 9,
+    "B-LDS": 35,
+    "B-LIT": 33,
+    "B-MRK": 37,
+    "B-ORG": 3,
+    "B-PER": 20,
+    "B-RR": 18,
+    "B-RS": 23,
+    "B-ST": 31,
+    "B-STR": 26,
+    "B-UN": 17,
+    "B-VO": 28,
+    "B-VS": 27,
+    "B-VT": 25,
+    "I-AN": 16,
+    "I-EUN": 10,
+    "I-GRT": 1,
+    "I-GS": 6,
+    "I-INN": 0,
+    "I-LD": 7,
+    "I-LDS": 5,
+    "I-LIT": 24,
+    "I-MRK": 22,
+    "I-ORG": 8,
+    "I-PER": 38,
+    "I-RR": 15,
+    "I-RS": 2,
+    "I-ST": 32,
+    "I-STR": 19,
+    "I-UN": 4,
+    "I-VO": 12,
+    "I-VS": 30,
+    "I-VT": 21,
+    "O": 34,
+    "PAD": 39
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de3c63fb08ef11b0b7f3c40b64084d5a2511d4c386ab6db1a51f4696f216d84
+size 434109392

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}