chart-captioning

A curated list of recent and past chart understanding work based on our IEEE TKDE survey paper: From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models.

Code and data for the ACL 2024 Findings paper "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning"

NLP and Deep Learning course project: generates financial alerts from news text and optional chart images, using BiLSTM-CRF NER, attention-based sentiment analysis (separate and joint models), DePlot + Qwen2.5 chart captioning, and rule-based or LLM alert generation.