How to Understand Named Entities: Using Common Sense for News Captioning

arXiv:2403.06520v1 Announce Type: new
Abstract: News captioning aims to describe an image with its news article body as input. It greatly relies on a set of detected named entities, including real-world people, organizations, and places. This paper exploits commonsense knowledge to understand named entities for news captioning. By ``understand'', we mean correlating the news content with common sense in the wild, which helps an agent to 1) distinguish semantically similar named entities and 2) describe named entities using words outside …

abstract article arxiv captioning common sense cs.ai cs.cl exploits image knowledge organizations paper people sense set type world