Paper: How Many Words Is a Picture Worth? Automatic Caption Generation for News Images

ACL ID P10-1126
Title How Many Words Is a Picture Worth? Automatic Caption Generation for News Images
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

In this paper we tackle the problem of au- tomatic caption generation for news im- ages. Our approach leverages the vast re- source of pictures available on the web and the fact that many of them are cap- tioned. Inspired by recent work in sum- marization, we propose extractive and ab- stractive caption generation models. They both operate over the output of a proba- bilistic image annotation model that pre- processes the pictures and suggests key- words to describe their content. Exper- imental results show that an abstractive model defined over phrases is superior to extractive methods.