OCR, extract and classify documents. In addition, annotate documents and build your own NLP and Computer Vision models using Python by downloading the data. Find examples in our Colab Notebooks, e. g. how to fine-tune Flair.

🗨️ This repository contains a collection of notebooks and resources for various NLP tasks using different architectures and frameworks.

notebooks to finetune `bert-small-amharic`, `bert-mini-amharic`, and `xlm-roberta-base` models using an Amharic text classification dataset and the transformers library

Jupyterlab Notebook for AI model creation for classifying inappropriate messages

The project utilizes Natural Language Processing (NLP) techniques to preprocess and analyze video transcripts, and employs a BERT + Bi-GRU model for text classification. The code is implemented in a Google Colab notebook.

Notebooks for handling text classification

This repository contains a single notebook, notebook.ipynb, which analyzes the ability of three machine learning algoithms — Multinomial Naive Bayes, Logistic Regression, and Support Vector Machine — to determine whether customer reviews of the Disneyland amusement park in California are positive or negative.

A repository dedicated to learning about Artificial Intelligence, Machine Learning, and Deep Learning using Python/IPython Notebook.

text classification, text to emotions notebook 🎨

This repository contains a Python script for sentiment analysis of tweets using a Multinomial Naive Bayes classifier. The code demonstrates a complete pipeline, from data loading and text pre-processing to model training and evaluation. It includes a Jupyter Notebook (or Python script) that can be used to analyze sentiment in tweets.

Notebooks Python da parte prática da disciplina "CIC0269 - Processamento de Linguagem Natural" do Departamento de Ciência da Computação da Universidade de Brasília.

Notebook for Flan-T5 – an alternative to large language models like GPT-3 & GPT-4 for NLP tasks like named entity recognition and text generation.

Notebook uses TensorFlow to finetune BERT for text classification task

This repository contains Jupyter notebooks detailing the experiments conducted in our research paper on Ukrainian news classification. We introduce a framework for simple classification dataset creation with minimal labeling effort, and further compare several pretrained models for the Ukrainian language.

SkimLit is a Natural Language Processing based model which includes different embeddings and architectures for processing the PubMed dataset. Links to the papers which include the dataset and the details of the architectures are mentioned in the Colab notebook

NLP demos and talks made with Jupyter Notebook and reveal.js

In this notebook, I am updating NLP notebooks, and projects

NLP 领域常见任务的实现，包括新词发现、以及基于pytorch的词向量、中文文本分类、实体识别、摘要文本生成、句子相似度判断、三元组抽取、预训练模型等。

Some demo sentiment analysis notebooks for my NLP students

In this notebook, I attempted to create a script that utilizes pre-trained CamemBERT and VaderSentiment models to label the sentiment of a Quran Karim dataset in English and French. My goal was to accurately classify the sentiment of each text sample in the dataset.