💡 TL;DR: Given an image and nothing else (i.e. no prompts or candidate labels), NOVIC can generate an accurate fine-grained textual classification label in real-time, with coverage of the vast ...

Abstract: The growing volume of unstructured text data in the banking sector has created a need for advanced classification methods to manage customer inquiries efficiently, resulting in faster ...

Abstract: Although graph neural networks based methods can solve the uneven text length problem of text classification datasets, they are difficult to address the data sparsity problem of short texts.

These days, our phones are constantly buzzing with notifications, and it's becoming increasingly difficult to distinguish between legitimate messages and potential scams. Bill from Mesa, Arizona, ...

This repository contains replication materials for Youngjin (YJ) Chae and Thomas Davidson. 2025. "Large Language Models for Text Classification: From Zero-Shot Learning to Instruction-Tuning." ...

Multi-label text classification (MLTC) assigns multiple relevant labels to a text. While deep learning models have achieved state-of-the-art results in this area, they require large amounts of labeled ...