End-to-End Conditional Poetry Generation

This project classifies Amazon Food comments into positive, neutral, or negative sentiments. It employs two methods: a Bag-of-Words approach using VADER and transformers encoder-decoder approach using T5.

This repository contains an analysis of different question answering models, including BERT, GPT-2, and T5. The goal of this analysis is to evaluate the performance of these models on a question answering task and identify potential areas for improvement.

T5 Language Models for the Indonesian Language!

Text Summarization using Pre-Trained T5 on News Dataset

Poster submitted by Pseudo Lab for ACH2021

Classification, ADSA and Text Summarisation based project for BridgeI2I Task at Inter IIT 2021 Competition. Silver Medalists.

Agentic RAG research assistant (LangChain + LangGraph + Hugging Face) that ingests PDFs and answers questions with citations. CPU-friendly T5 baseline, Chroma vector store, and a critic-revise loop

Neural network / AI models / LLM models - implementations from scratch in pytorch

Banned or no internet connection? Use this simple loader to bypass the official Plutonium loader.

👨‍🎓 This repo is a supplement to my video on Transformers and Text Summarization as part of my series AI does AI (https://youtu.be/p_6xgrykPMQ)

UBC-NLP/AraT5v2-base-1024 finetuned for hate speech classification

The repository contains model implementations and data described in the paper: From Dataset Recycling to Multi-Property Extraction and Beyond.

Перефразатор

Research Assistant Mini App

Unlock the depths of Wikipedia with WikiBot. It delivers concise summaries and suggests related articles to fuel your curiosity and guide your exploration.

Repository for the paper "ViHateT5: Enhancing Hate Speech Detection in Vietnamese with A Unified Text-to-Text Transformer Model" (ACL'2024 - Findings)

Solution for Kaggle's LLM prompt recovery.