{"id":21681707,"url":"https://github.com/jersongb22/questionanswering-tensorflow","last_synced_at":"2026-05-06T22:35:38.815Z","repository":{"id":246147129,"uuid":"818851007","full_name":"JersonGB22/QuestionAnswering-TensorFlow","owner":"JersonGB22","description":null,"archived":false,"fork":false,"pushed_at":"2024-06-26T17:51:57.000Z","size":2165,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-25T11:25:46.294Z","etag":null,"topics":["hugging-face","plotly","python","question-answering","roberta-large","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JersonGB22.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-06-23T03:56:36.000Z","updated_at":"2024-06-26T18:05:00.000Z","dependencies_parsed_at":"2024-06-26T05:47:40.217Z","dependency_job_id":"ecc62d83-b03d-4e5e-b9fe-4e93649e2f97","html_url":"https://github.com/JersonGB22/QuestionAnswering-TensorFlow","commit_stats":null,"previous_names":["jersongb22/questionanswering-tensorflow"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JersonGB22%2FQuestionAnswering-TensorFlow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JersonGB22%2FQuestionAnswering-TensorFlow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JersonGB22%2FQuestionAnswering-TensorFlow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JersonGB22%2FQuestionAnswering-TensorFlow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JersonGB22","download_url":"https://codeload.github.com/JersonGB22/QuestionAnswering-TensorFlow/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244600674,"owners_count":20479304,"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":["hugging-face","plotly","python","question-answering","roberta-large","tensorflow"],"created_at":"2024-11-25T15:30:53.294Z","updated_at":"2026-05-06T22:35:38.778Z","avatar_url":"https://github.com/JersonGB22.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# \u003ch1 align=\"center\"\u003e**Question Answering**\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"images/image_readme.png\"\u003e \n\u003c/p\u003e\n\nThis repository implements Question Answering models, a natural language processing (NLP) task that retrieves the answer to a question from a given text. These models are created using the TensorFlow and Hugging Face Transformers libraries. There are two types of this task:\n\n1. **Extractive:** Extracts the answer directly from the provided context.\n2. **Abstractive:** Generates a correct answer freely based on the context or without it.\n\n## **Common Use Cases:**\n- **Virtual Assistants:** Answering user questions using information from a specific database.\n- **Document Search:** Finding precise answers in large document sets.\n- **Customer Service:** Providing quick and accurate responses to customer inquiries.\n- **Education:** Helping students get answers to questions based on study materials.\n\n## **Implemented Models:**\n\n- **Extractive Model for Answerable Questions:** This RoBERTa Large model has been fine-tuned with the [Stanford Question Answering Dataset (SQuAD)](https://huggingface.co/datasets/rajpurkar/squad) to appropriately answer questions within a given context. SQuAD consists of 100,000 question-answer pairs across more than 500 Wikipedia articles, where the answer is a text segment from the corresponding passage. The model has achieved an excellent **F1 Score** of **94.1%** on the validation set.\n\n- **Extractive Model for Answerable and Unanswerable Questions:** This model is a more robust and challenging version of the previous one, fine-tuned with [SQuAD 2.0](https://huggingface.co/datasets/rajpurkar/squad_v2) to appropriately answer both answerable and unanswerable questions within the provided context. SQuAD 2.0 consists of the 100,000 question-answer pairs from SQuAD plus 50,000 unanswerable questions. The model is capable of responding to questions within the context and also returns ``No Answer`` if the answer is not in the context or if it is of an abstractive type. It has achieved an excellent **F1 Score** of **87.7%** on the validation set.\n\n## **Some Results**\n\n\u003cp align=\"left\"\u003e\n\u003cimg src=\"images/images_models/prediction_qa_val_2.png\" style=\"width: 1249px;\"\u003e \n\u003c/p\u003e\n\n---\n\u003cp align=\"left\"\u003e\n\u003cimg src=\"images/images_models/prediction_qa_val_1.png\" style=\"width: 1238px;\"\u003e \n\u003c/p\u003e\n\n---\n\u003cp align=\"left\"\u003e\n\u003cimg src=\"images/images_models/prediction_qa_matrix.png\" style=\"width: 1366px;\"\u003e \n\u003c/p\u003e\n\n---\n\u003cp align=\"left\"\u003e\n\u003cimg src=\"images/images_models/prediction_qa_worldwar2.png\" style=\"width: 1366px;\"\u003e \n\u003c/p\u003e\n\n#### *Further results can be found in their respective notebooks.*\n\n## **Technological Stack**\n[![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge\u0026logo=python\u0026logoColor=white\u0026labelColor=101010)](https://docs.python.org/3/) \n[![TensorFlow](https://img.shields.io/badge/TensorFlow-FF6F00?style=for-the-badge\u0026logo=tensorflow\u0026logoColor=white\u0026labelColor=101010)](https://www.tensorflow.org/api_docs)\n[![Hugging Face](https://img.shields.io/badge/Hugging%20Face-FFD21E?style=for-the-badge\u0026logo=huggingface\u0026logoColor=white\u0026labelColor=101010)](https://huggingface.co/)\n[![Plotly](https://img.shields.io/badge/Plotly-3F4F75?style=for-the-badge\u0026logo=plotly\u0026logoColor=white\u0026labelColor=101010)](https://plotly.com/)\n\n## **Contact**\n[![Gmail](https://img.shields.io/badge/Gmail-D14836?style=for-the-badge\u0026logo=gmail\u0026logoColor=white\u0026labelColor=101010)](mailto:jerson.gimenesbeltran@gmail.com)\n[![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge\u0026logo=linkedin\u0026logoColor=white\u0026labelColor=101010)](https://www.linkedin.com/in/jerson-gimenes-beltran/)\n[![GitHub](https://img.shields.io/badge/GitHub-181717?style=for-the-badge\u0026logo=github\u0026logoColor=white\u0026labelColor=101010)](https://github.com/JersonGB22/)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjersongb22%2Fquestionanswering-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjersongb22%2Fquestionanswering-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjersongb22%2Fquestionanswering-tensorflow/lists"}