Material for my VLDB'22 and BTW'23 tutorials on application for language models in data management
-
Updated
Dec 18, 2024 - HTML
Material for my VLDB'22 and BTW'23 tutorials on application for language models in data management
Space Model framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. It is an external LLM layer, that improves accuracy in classification task for multiple datasets, such as HateXplain, IMDB movies reviews and more.
Fill-in-the-BERT uses pre-trained BERT Masked Language Model for Infering the task of fill in the blanks.
Disease detection from textual description. We created a dataset containing 24 disease and 50 manually written descriptions of the symptoms (in english) for each disease.
Topic Modelling using Transformers
Pro/Anti-vaxxers in Brazil: a temporal analysis of COVID vaccination stance in Twitter
Kaggle Competition - Natural Language Processing with Disaster Tweets
A Case Study On The Rising Omicron Cases and Public Sentiment Analysis using Twitter Data
A tiny NLP demo on how to summarize swedish texts using the BERT model from the National Library of Sweden.
The main idea of this project is of Transfer Learning. Bert large 24 encoder Questions Answering model was fine tuned on specific task of Questions Answering. Currently for Demo purposes it is Hosted on free Heroku platform. Please take a moment to catch up the twisting idea.
This is a application to analyse toxicity in social media using BERT and context analysis and aims to reduce toxicity
Software based on flask, used to check the most similar texts out of a list.
Topic modelling of invoice data
Predicting similarity of texts using transformers
Neutral Net is a Flask web application developed for the COS398 Ethics and Social Impacts of Computing course at the University of Southern Maine. This application utilizes SerpAPI and a fine-tuned BERT model to analyze Google search results for bias.
AI-Driven Investment Insights by Financial Headline Sentiment Analysis
Multi-label classification of hate speech targets using deep learning, including dataset preprocessing, benchmark tools, and PyTorch-based models.
Flask application for sentiment detection using LLMs
This project is a web application that classifies whether an essay is written by a human or generated by AI using BERT model.
Real-time vulnerability detection for web3 smart contracts
Add a description, image, and links to the bert-model topic page so that developers can more easily learn about it.
To associate your repository with the bert-model topic, visit your repo's landing page and select "manage topics."