initial commit for wikiser-bert-large

README.md

@@ -1,3 +1,65 @@
 ---
+tags:
+- software engineering
+- ner
+- named-entity recognition
+- token-classification
+widget:
+- text: >-
+        In 2005, Nokia developed a Linux-based operating system called Maemo, which shipped that year on the Nokia 770 Internet Tablet.
+  example_title: example 1
+- text: >-
+        The Linux kernel is a widely ported operating system kernela and runs on a highly diverse range of computer architectures, including ARM-based Android smartphones and the IBM Z mainframes.
+  example_title: example 2
+- text: >-
+        Windows XP was originally bundled with Internet Explorer 6.
+  example_title: example 3
+language:
+- en
+datasets:
+- wikiser
 license: apache-2.0
 ---
+# Software Entity Recognition with Noise-robust Learning
+
+We train a BERT model for the task software entity recognition (SER).
+The training data leverages WikiSER, a corpus of 1.7M sentences extracted from Wikipedia.
+The model uses _self-regularization_ during the finetuning process, allowing it to be robust to texts in the software domain, including misannotations, different naming conventions, and others.
+
+The model recognizes 12 fine-grained named entities: `Algorithm`, `Application`, `Architecture`, `Data_Structure`, `Device`, `Error_Name`, `General_Concept`, `Language`,
+`Library`, `License`, `Operating_System`, and `Protocol`.
+
+## Model details
+
+Paper: Coming...
+
+Code: https://github.com/taidnguyen/software_entity_recognition
+
+Finetuned from model: `bert-large-cased`
+
+## How to use
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+tokenizer = AutoTokenizer.from_pretrained("taidng/wikiser-bert-large")
+model = AutoModelForTokenClassification.from_pretrained("taidng/wikiser-bert-large")
+
+nlp = pipeline("ner", model=model, tokenizer=tokenizer)
+example = "Windows XP was originally bundled with Internet Explorer 6."
+
+ner_results = nlp(example)
+print(ner_results)
+```
+
+## Citation
+
+```bibtex
+@inproceedings{nguyen2023software,
+  title={Software Entity Recognition with Noise-Robust Learning},
+  author={Nguyen, Tai and Di, Yifeng and Lee, Joohan and Chen, Muhao and Zhang, Tianyi},
+  booktitle={Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE'23)},
+  year={2023},
+  organization={IEEE/ACM}
+}
+```

config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-Algorithm",
+    "1": "I-Algorithm",
+    "2": "B-Application",
+    "3": "I-Application",
+    "4": "B-Architecture",
+    "5": "I-Architecture",
+    "6": "B-Data_Structure",
+    "7": "I-Data_Structure",
+    "8": "B-Device",
+    "9": "I-Device",
+    "10": "B-Error_Name",
+    "11": "I-Error_Name",
+    "12": "B-General_Concept",
+    "13": "I-General_Concept",
+    "14": "B-Language",
+    "15": "I-Language",
+    "16": "B-Library",
+    "17": "I-Library",
+    "18": "B-License",
+    "19": "I-License",
+    "20": "B-Operating_System",
+    "21": "I-Operating_System",
+    "22": "B-Protocol",
+    "23": "I-Protocol",
+    "24": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Algorithm": 0,
+    "B-Application": 2,
+    "B-Architecture": 4,
+    "B-Data_Structure": 6,
+    "B-Device": 8,
+    "B-Error_Name": 10,
+    "B-General_Concept": 12,
+    "B-Language": 14,
+    "B-Library": 16,
+    "B-License": 18,
+    "B-Operating_System": 20,
+    "B-Protocol": 22,
+    "I-Algorithm": 1,
+    "I-Application": 3,
+    "I-Architecture": 5,
+    "I-Data_Structure": 7,
+    "I-Device": 9,
+    "I-Error_Name": 11,
+    "I-General_Concept": 13,
+    "I-Language": 15,
+    "I-Library": 17,
+    "I-License": 19,
+    "I-Operating_System": 21,
+    "I-Protocol": 23,
+    "O": 24
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "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 sha256:2e3a8827bee2737c3c308deb9f112d3db802522d1aab81ce7b932a08115a6fc7
+size 1330359341

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 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding": "max_length",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}