{"id":16102991,"url":"https://github.com/ayushk4/ner_lab_protocols","last_synced_at":"2025-08-13T19:45:30.504Z","repository":{"id":67286953,"uuid":"300494946","full_name":"Ayushk4/NER_Lab_Protocols","owner":"Ayushk4","description":null,"archived":false,"fork":false,"pushed_at":"2020-10-02T04:00:08.000Z","size":4577,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-12T07:30:12.953Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ayushk4.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-10-02T03:56:56.000Z","updated_at":"2020-10-02T04:00:10.000Z","dependencies_parsed_at":"2023-02-21T01:45:16.422Z","dependency_job_id":null,"html_url":"https://github.com/Ayushk4/NER_Lab_Protocols","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ayushk4%2FNER_Lab_Protocols","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ayushk4%2FNER_Lab_Protocols/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ayushk4%2FNER_Lab_Protocols/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ayushk4%2FNER_Lab_Protocols/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ayushk4","download_url":"https://codeload.github.com/Ayushk4/NER_Lab_Protocols/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247422161,"owners_count":20936430,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-09T18:55:12.977Z","updated_at":"2025-04-06T01:25:00.314Z","avatar_url":"https://github.com/Ayushk4.png","language":"Python","readme":"# Named Entity Recognition of lab protocols\nAuthors: [Ayush Kaushal](https://github.com/Ayushk4)  and [Tejas Vaidhya](https://github.com/tejasvaidhyadev)\n\nCode for the system that secured 4 runner up at EMNLP 2020 workshop WNUT Shared Task-3\n\nFor more derail refer [shared task website](http://noisy-text.github.io/2020/wlp-task.html)\n\n**Code Credits**: [BERT_NER](https://github.com/weizhepei/BERT-NER)\n\n## Dependencies and setup\n\n- python 3.8 conda `create --name protocol_NER python=3.8 \u0026 conda activate protocol_NER`\n- PyTorch 1.5.0, cudatoolkit=10.1 `conda install pytorch==1.5.0 cudatoolkit=10.1 -c pytorch`\n- 🤗Huggingface transformers 2.9.0 `pip install transformers==2.9.0`\n- scikit-learn 0.23.1 `pip install scikit-learn==0.23.1`\n- nltk 3.5 `pip install nltk==3.5`\n\n## Model Description \n![Bio-Bert](./asset/Bio-BERT.png)\n\n## Instruction for training the models\n0. Set up the codebase and requirements\n    -`git clone https://github.com/tejasvaidhyadev/W-NUT_2020.git` \u0026 `cd W-NUT_2020.`\n    - Follow the instructions from the Dependencies and `set-up` above to install the dependencies.\n1. Setup the dataset : Fllow instruction in `./data/README.md`\n\n2. Recreating the experiment for the final submission:\n    -run `python train.py` --dataset=proto (BERT model will be automatically chosen (for now Bio-BERT). It will instantiate a model and train it on the training set following the hyper-parameters specified in `experiment/proto/params.json`. )\n    - preprocessing of Dataset for bert input refer `./data/Readme.md`\n\n**We release the models weights for our final submission.**\n\n- [**Bio-BERT model**](https://github.com/tejasvaidhyadev/W-NUT_2020/releases/download/v0.0.1/biobert-onfinaldata.zip)\n- Download and extract the file into `./experiment/proto/`\n\n## Model Performance \nModel Performance on test set released for final evaluation using organisers [script](https://github.com/jeniyat/WNUT_2020_NER/tree/master/code/eval) (exact match)\n**On exact matches**\n\n| Entity          | Precision | Recall | F1    |\n| --------------- | --------- | ------ | ----- |\n| Action          | 87.85     | 85.2   | 86.5  |\n| Amount          | 72.25     | 93.78  | 81.62 |\n| Concentration   | 84.27     | 91.21  | 87.6  |\n| Device          | 65.2      | 58.4   | 61.61 |\n| Generic-Measure | 28.74     | 40.34  | 33.57 |\n| Location        | 62.89     | 71.14  | 66.76 |\n| Measure         | 66.73     | 51.3   | 58.0  |\n| Mention         | 66.43     | 64.14  | 65.26 |\n| Method          | 45.98     | 42.53  | 44.19 |\n| Modifier        | 73.33     | 46.43  | 56.86 |\n| Numerical       | 66.15     | 49.62  | 56.7  |\n| Reagent         | 80.47     | 84.13  | 82.26 |\n| Seal            | 72.45     | 59.66  | 65.44 |\n| Size            | 54.93     | 16.39  | 25.24 |\n| Speed           | 87.01     | 92.08  | 89.47 |\n| Temperature     | 92.94     | 86.58  | 89.65 |\n| Time            | 90.27     | 86.13  | 88.15 |\n|pH               |   95.16   | 89.39  | 92.19 |\n\n**On partial matches **\n\n| Overall         | Precision | Recall | F1    |\n| --------------- | --------- | ------ | ----- |\n| partial matches | 81.76     | 77.43  | 79.54 |\n| exact matches   | 77        | 72.93  | 74.91 |\n\n\n\n\n## Coming Soon!\n\n- Instructions for running our trained models on test set\n- Details about our model architecture.\n- Replicating our other experiments.\n\n## License\nMIT\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayushk4%2Fner_lab_protocols","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fayushk4%2Fner_lab_protocols","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayushk4%2Fner_lab_protocols/lists"}