A Chat Moderation Bot for Discord

An approach to extracting and summarizing key infrastructure and community impact information from wind disaster reconnaissance reports using Zero-shot text classification with BART-large models, highlighted by keywords.

The goal here is to develop a simple mock web app book library for demonstrating a possible use of AI for aiding users

LLMs for Low Resource Languages in Multilingual, Multimodal and Dialectal Settings

Comparing zero-shot and fine-tuned text classification transformer models across different review datasets

Applying zero-shot learning on classification task.

Generalized Zero-Shot Character Recognition

Trying out with HuggingFace Models

Exploring fast & accurate zero-shot text classification

Various NLP tasks for Global Health Analysis, including an automatic Named Entity Recognition (NER) pipeline to annotate Global Digital Health Documents.

BioCLIP base model for use with Autodistill.

FastViT base model for use with Autodistill.

To check the frequency of an entity from the data and to classify the data in terms of negative and positive with their polarity scores.

We propose a novel method of fine-tuning the model for a particular downstream task, which proves to be more efficient and generalizable. We show that in an example of a fake news detection task, utilizing three distinct datasets and outperforming the baseline model in both the same dataset and cross-dataset zero-shot test.

CS410 Tech Review - X-Class for classifying biology papers with biomimicry functions

2022 Silicon Valley Internship (IT23)

How to use Zero-Shot Learning for Text Classification

Writing your beancount files with AI!

a mini zero-shot text classification implementation using streamlit and transformers