Code for training and generating inferences from a fine-tuned GPT2 model. The model is specifically trained on code and natural language data to generate code snippets given natural language prompts.

Docker with Flash app and Yandex speechkit for remote play text to speech

Sentiment Analysis on Tweets based on Recurrent Neural Network and attention model, implemented using Tensorflow library.

Spam filter program implemented with python from scratch and sklearn tool

turn natural language into structured data

Sab-AI Lab is a boutique AI and machine learning lab in Nagoya-Japan.

small steps towards true artificial intelligence

Projeto open source para criação de videos automáticos

Code repository related to various research and development experiments for the NLU component of a Romanian home assistant. Fork from the research group's repo.

Learning techniques related to NLP

This application can detect the hate and toxic tweets of users amongst an entire corpora of tweets and thus can be an effective methodology towards reducing cyber bullying.

Download corpus, preprocessing data and training GloVe all-in-one

🧠 Kurz Umelá Inteligencia (Artificial Intelligence AI) - Materiály, zdroje, skripty k večernému online kurzu/workshopu pre Impact Hub/Google

A Voice User Interface tool for Text-to-Speech and Speech-to-Text, built with Python and Django Framework, to solve the proposed exercise in "Cognitive Computing 2: Voice User Interface" discipline.

Data Paradox is a team of data science and associated research enthusiasts.

Processing, correction, and classification of spanish text with word embedding and GRU bidirectional net.

This repository is from my own nature_inspired_programming repository. I just decided to make it a separate repository. This is an implementation of custom natural language preprocessing for AutoML library tpot.

Code for Findings of ACL 2023 paper "Exploiting Rich Textual User-Product Context for Improving Personalized Sentiment Analysis"

A TensorFlow-compatible Python library that provides models and layers to implement custom Transformer neural networks. Built on TensorFlow 2.

Question-answering dataset to evaluate reasoning ability over short paragraphs.