initial commit

.gitignore

@@ -0,0 +1,45 @@
+# Ignore Python cache and compiled files
+__pycache__/
+*.py[cod]
+*.pyo
+
+# Ignore logs
+*.log
+logs/
+*.out
+
+# Ignore prediction files (JSON format)
+*.json
+
+# Ignore environment and dependency files
+.env
+*.env
+*.venv
+venv/
+ENV/
+*.lock
+
+# Ignore Jupyter Notebook checkpoints
+.ipynb_checkpoints
+
+# Ignore temporary or backup files
+*.bak
+*.swp
+*.tmp
+
+# Ignore OS-specific files
+.DS_Store
+Thumbs.db
+
+# Ignore model checkpoint files (optional)
+checkpoint/
+*.ckpt
+
+# If using Hugging Face Model repository, don't ignore the following:
+!config.json
+!label_list.json
+!tokenizer_config.json
+!tokenizer.json
+!special_tokens.json
+!added_tokens.json
+!pytorch_model.bin

README.md

@@ -10,4 +10,36 @@ base_model:
 - microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
 pipeline_tag: text-classification
 library_name: transformers
----
+---
+
+# Fine-tuned RE Model for DiMB-RE
+
+## Model Description
+This is a fine-tuned **Relation Extraction (RE)** model based on the [BiomedNLP-BiomedBERT-base-uncased](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) model, specifically designed for sentence classification task to extract relations between extract entities for diet, human metabolism and microbiome field. The model has been trained on the DiMB-RE dataset and is optimized to infer relationship with 13 relation types.
+
+<!-- ### Key Features:
+- **Language**: English
+- **Task**: Token classification for Named Entity Recognition (NER)
+- **Base Model**: BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
+- **Domains**: Biomedical, Clinical, Scientific -->
+
+## Performance
+The model has been evaluated on the DiMB-RE using the following metrics:
+- **Relation with Factuality (w/ GOLD relations)** - P: 0.926, R: 0.843, F1: 0.883
+- **Relation with Factuality (Strict, end-to-end w/ predicted entities and relations)** - P: 0.399, R: 0.322, F1: 0.356
+- **Relation with Factuality (Relaxed, end-to-end w/ predicted entities and relations)** - P: 0.440, R: 0.355, F1: 0.393
+
+## Citation
+If you use this model, please cite like below:
+
+```bibtex
+@misc{hong2024dimbreminingscientificliterature,
+      title={DiMB-RE: Mining the Scientific Literature for Diet-Microbiome Associations}, 
+      author={Gibong Hong and Veronica Hindle and Nadine M. Veasley and Hannah D. Holscher and Halil Kilicoglu},
+      year={2024},
+      eprint={2409.19581},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2409.19581}, 
+}
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForRelation"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30766
+}

label_list.json

@@ -0,0 +1 @@
+["no_certainty", "Factual", "Negated", "Unknown"]

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b2e5389239af01ec02982f5a9b7abe5dfbb4f27b9164e5f756e103c0a1c075
+size 438757552

special_tokens.json

@@ -0,0 +1 @@
+{}