{"id":26993327,"url":"https://github.com/yahiazakaria445/arabic-answer-grading-using-sequence-models","last_synced_at":"2025-10-08T00:05:20.323Z","repository":{"id":281674700,"uuid":"946015358","full_name":"yahiazakaria445/Arabic-Answer-Grading-using-Sequence-Models","owner":"yahiazakaria445","description":"An NLP project on Arabic data using LSTM model","archived":false,"fork":false,"pushed_at":"2025-03-10T14:17:51.000Z","size":139,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-03T23:18:11.772Z","etag":null,"topics":["matplotlib","nltk","numpy","pandas","scikit-learn","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/yahiazakaria445.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":"2025-03-10T13:33:13.000Z","updated_at":"2025-03-22T12:22:42.000Z","dependencies_parsed_at":"2025-03-10T15:30:41.880Z","dependency_job_id":"fabf6068-7b48-42cd-9e95-887547a8a83e","html_url":"https://github.com/yahiazakaria445/Arabic-Answer-Grading-using-Sequence-Models","commit_stats":null,"previous_names":["yahiazakaria445/automatic-arabic-answer-grading-using-sequence-models","yahiazakaria445/arabic-answer-grading-using-sequence-models"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FArabic-Answer-Grading-using-Sequence-Models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FArabic-Answer-Grading-using-Sequence-Models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FArabic-Answer-Grading-using-Sequence-Models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FArabic-Answer-Grading-using-Sequence-Models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yahiazakaria445","download_url":"https://codeload.github.com/yahiazakaria445/Arabic-Answer-Grading-using-Sequence-Models/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247092383,"owners_count":20882218,"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":["matplotlib","nltk","numpy","pandas","scikit-learn","tensorflow"],"created_at":"2025-04-03T23:18:14.656Z","updated_at":"2025-10-08T00:05:15.054Z","avatar_url":"https://github.com/yahiazakaria445.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"This project focuses on automatically grading short Arabic answers using advanced Natural Language Processing (NLP) techniques and sequence models such as LSTM.\n\n# Dataset\nThis project uses The ARabic Dataset for Automatic Short Answer Grading Evaluation \nThis dataset is intended for exploring research in the field of Automatic Short Answer Grading (ASAG).\n[Dataset Link](https://github.com/leilaouahrani/AR-ASAG-Dataset)\n\n# libraries used\n- numpy  \n- pandas  \n- matplotlib  \n- seaborn  \n- nltk  \n- scikit-learn  \n- keras  \n- tensorflow \n\n# Text Preprocessing\nArabic text is cleaned, normalized, and tokenized to handle linguistic variations such as diacritics, punctuation, and synonyms. Using `Tokenizer`, text is converted into sequences of tokens (integers), and then `pad_sequences` is applied to ensure all input sequences have a uniform length, which is essential for feeding data into model.\n\n# texts_to_sequences \u0026 Word Embedding\nAfter preprocessing the text, the `Tokenizer` is used to convert words into numerical sequences using the `texts_to_sequences` method. These sequences are then padded to ensure consistent input length. The resulting sequences are passed through a word embedding layer (`Word2Vec`) allowing the model to represent each word in a dense vector space that captures semantic and contextual relationships. This encoding forms the foundation for LSTM sequence model input.\n\n# Model Architecture\n| model  | optimizer | metrics |loss function  |accuracy score|\n| -------- | -------- | -------- | -------- |-------- |\n|  LSTM    | adam   |accuracy score    |categorical crossentropy    |85%\n\n# testing sample\n|answer| rate |\n| -------- | -------- |\n| 1    | B   |\n|2    | A| \n| 3   | D   |\n| a  | B   |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyahiazakaria445%2Farabic-answer-grading-using-sequence-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyahiazakaria445%2Farabic-answer-grading-using-sequence-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyahiazakaria445%2Farabic-answer-grading-using-sequence-models/lists"}