{"id":26612380,"url":"https://github.com/kgelli/nlp-qa-chatbot","last_synced_at":"2026-05-18T19:02:02.391Z","repository":{"id":259688088,"uuid":"879206484","full_name":"kgelli/NLP-QA-Chatbot","owner":"kgelli","description":"A neural network chatbot that answers questions about stories using memory networks trained on the Facebook Babi dataset.","archived":false,"fork":false,"pushed_at":"2025-03-05T09:30:39.000Z","size":1774,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-24T03:18:04.893Z","etag":null,"topics":["chatbot","deep-learning","keras","memory-networks","neural-networks","nlp"],"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/kgelli.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":"2024-10-27T09:47:31.000Z","updated_at":"2025-03-05T09:38:27.000Z","dependencies_parsed_at":"2024-10-27T11:08:02.432Z","dependency_job_id":"62e032ee-53a8-4042-b3df-de06306b6d35","html_url":"https://github.com/kgelli/NLP-QA-Chatbot","commit_stats":null,"previous_names":["kgelli/chat-bots"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kgelli%2FNLP-QA-Chatbot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kgelli%2FNLP-QA-Chatbot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kgelli%2FNLP-QA-Chatbot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kgelli%2FNLP-QA-Chatbot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kgelli","download_url":"https://codeload.github.com/kgelli/NLP-QA-Chatbot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kgelli%2FNLP-QA-Chatbot/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259186472,"owners_count":22818572,"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":["chatbot","deep-learning","keras","memory-networks","neural-networks","nlp"],"created_at":"2025-03-24T03:18:14.298Z","updated_at":"2025-10-13T10:17:33.523Z","avatar_url":"https://github.com/kgelli.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Question-Answer Chat Bot\n\nA simple question-answering chatbot built using neural networks to understand and respond to queries about object locations and movements.\n\n## Project Overview\n\nThis project implements a memory network model that can answer simple questions about stories. The chatbot is trained on the Facebook Babi dataset, which consists of short stories followed by questions.\n\n## Features\n\n- End-to-end memory network architecture\n- Processes natural language questions about object locations\n- Provides yes/no answers with probability of certainty\n- Supports custom stories and questions using vocabulary from the training data\n\n## Model Architecture\n\nThe model uses:\n- Embedding layers to convert words to vectors\n- Memory encoding for both stories and questions\n- Attention mechanism to focus on relevant parts of the story\n- LSTM layer to process the combined information\n- Softmax output layer for final prediction\n\n## Dataset\n\nThe model is trained on the Facebook Babi dataset which includes:\n- 10,000 training examples\n- 1,000 test examples\n- Simple stories about people and objects moving between locations\n\n## Requirements\n\n- Python 3\n- TensorFlow/Keras\n- NumPy\n- Matplotlib\n- Pickle\n\n## Usage\n\n1. Train the model or use the pre-trained weights (chatbot_120_epochs.h5)\n2. Input stories and questions using vocabulary from the dataset\n3. Get predictions with confidence scores\n\n## Example\n\n```python\nmy_story = \"John left the kitchen. Sandra dropped the football in the garden.\"\nmy_question = \"Is the football in the garden?\"\n\n# Result\n# Predicted answer is: yes\n# Probability of certainty was: 0.97079676\n```\n\n## Performance\n\nThe model achieves over 90% accuracy on the test dataset after 120 epochs of training.\n\n## Limitations\n\n- Limited to the vocabulary in the training dataset\n- Only handles yes/no questions\n- Designed for simple, direct questions about object locations\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkgelli%2Fnlp-qa-chatbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkgelli%2Fnlp-qa-chatbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkgelli%2Fnlp-qa-chatbot/lists"}