Experiments with (German) text classification using state-of-the-art Deep Learning approaches.
-
Updated
Feb 3, 2022 - Jupyter Notebook
#
nlp-classification
Here are 11 public repositories matching this topic...
Solution to sample NLP challenge at Kaggle
nlp python3 pytorch kaggle-competition bert onnx fastapi huggingface-transformers nlp-classification
-
Updated
Aug 14, 2022 - Jupyter Notebook
2022 HAI 1팀 프로젝트 방언 번역기 개발을 위한 레포지토리입니다.
-
Updated
Dec 1, 2022 - Jupyter Notebook
An unsupervised automated bookkeeping data pipeline that cleans bank SMS text notifications, eliminates "Garbage In, Garbage Out" errors, clusters rows using K-Means, and streams analytics data dashboards to a live Streamlit interface. Created by Srinivasta.
scikit-learn kmeans unsupervised-learning data-cleaning data-pipeline text-clustering streamlit financial-analytics nlp-classification xero-integration automated-bookkeeping anti-gigo
-
Updated
Jun 26, 2026 - Python
This is a production-ready, end-to-end system developed to detect and classify racist tweets using advanced Natural Language Processing (NLP) techniques. Built on top of BERTweet (vinai/bertweet-base) and fine-tuned with a robust, k-fold cross-validation training pipeline, powered by streamlit UI!
python nlp machine-learning deep-learning text-classification transformers inference transfer-learning ai-ethics responsible-ai huggingface streamlit-webapp bertweet nlp-classification toxic-language-detection confusion-matrix-analysis interactive-applications class-imbalance-handling classification-report-analysis
-
Updated
Jul 23, 2025 - Python
GePart: German Party Classification Model. Student project during the 5th and 6th semester.
-
Updated
Jul 30, 2023 - TeX
Built a scikit-learn ML pipeline to automate IT ticket routing. Cleans raw data errors and accurately classifies text to direct requests to the correct department, resulting in FastAPI deployment.
machine-learning scikit-learn tf-idf nlp-machine-learning api-deployment fastapi nlp-classification one-versus-all-comparison-method
-
Updated
Jul 11, 2026 - Jupyter Notebook
An end-to-end credibility analysis platform that uses an ensemble of classic Machine Learning (Linear SVM) and Deep Learning (RoBERTa Transformer) to detect fake news in real-time. Features a React dashboard, automatic URL article scraping, model comparison views, and contextual reasoning insights.
react machine-learning natural-language-processing typescript web-scraping ensemble-learning svm-classifier fastapi fake-news-detection nlp-classification roberta-transformer data-debiasing
-
Updated
Jun 15, 2026 - Python
NLP Transformer pipeline + LLM QA with RAG - Homeworks for BigData Team NLP course on LLMs
nlp transformer question-answering attention-mechanism nlp-machine-learning faiss wandb huggingface-transformers nlp-classification large-language-models llm retrieval-augmented-generation llm-qa-document llm-rag
-
Updated
May 2, 2025 - Jupyter Notebook
This project focuses on detecting disaster-related tweets using machine learning. The dataset, sourced from Kaggle, contains 7613 tweets labeled as disaster-related or not. Various Natural Language Processing (NLP) techniques and machine learning models were applied to classify these tweets accurately.
data-science machine-learning natural-language-processing random-forest text-classification svm lightgbm logistic-regression bert disaster-response huggingface nlp-classification
-
Updated
Apr 7, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the nlp-classification topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nlp-classification topic, visit your repo's landing page and select "manage topics."