Topic clustering library built on Transformer embeddings and cosine similarity metrics.Compatible with all BERT base transformers from huggingface.

This work focuses on the development of machine learning models, in particular neural networks and SVM, where they can detect toxicity in comments. The topics we will be dealing with: a) Cost-sensitive learning, b) Class imbalance

Tutorial on training a RoBERTa Transformers model from scratch

Building this project to generate MCQ Questions from any type of text and generate answers and distractors for it.

Convert pretrained RoBerta models to various long-document transformer models

It is the nlp task to classify empathetic dialogues datasets using RoBERTa, ERNIE-2.0 and XLNet with different preprocessing method. You can get some detailed introduction and experimental results in the link below.

[NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach'.

Generating code with Ludwig AI/ML (PyTorch, Tensorflow)

The purpose of this repository is to introduce new dialogue-level commonsense inference datasets and tasks. We chose dialogues as the data source because dialogues are known to be complex and rich in commonsense.

Best project ever

A safe social media webapp using NLP models(BERT and GPT3) for bad language detection and content recommendations, deployed using docker and Kubernetes on digital ocean

This app Classifies the text generated by AI tools like chatGPT. Roberta-base-openai-detector Model has been used from hugging face to detect ai generated texts.

This project analyzes tweets about electronic products using ReBERTa, Kafka, Logstash, Elasticsearch, and Kibana for sentiment analysis and data visualization.

This repository contains the code of our winning solution for the Shared Task on Detecting Signs of Depression from Social Media Text at LT-EDI-ACL2022.

Resources for the paper: Monolingual Pre-trained Language Models for Tigrinya

Source code for CoNLL 2021 paper by Huebner et al. 2021

This repository contains the solutions to three problem statements completed during the hackathon. Each problem statement is categorized based on its difficulty level: Easy, Moderate, and Hard.

Sentiment Analysis using roBERTa

This repository contains the code, models and corpus of the project "Generative Adversarial Networks for Text-to-Image Synthesis & Generation: A Comparative Analysis of Natural Language Processing models for the Spanish language".

BIRBAL.AI is a dynamic Gen AI-infused Interactive & Analytical Dashboard. Leveraging Meta’s Llama2, and RoBERTa alongside PygWalker for NLP-based Sentiment Analysis, Its AI Insights Engine pioneers Multi-Lingual & Voice interactive analytics, utilizing Bhashini APIs and Meta’s Llama2 across all 22 official languages of India