Sciweavers

Share
ACL
2010

Generating Image Descriptions Using Dependency Relational Patterns

9 years 21 days ago
Generating Image Descriptions Using Dependency Relational Patterns
This paper presents a novel approach to automatic captioning of geo-tagged images by summarizing multiple webdocuments that contain information related to an image's location. The summarizer is biased by dependency pattern models towards sentences which contain features typically provided for different scene types such as those of churches, bridges, etc. Our results show that summaries biased by dependency pattern models lead to significantly higher ROUGE scores than both n-gram language models reported in previous work and also Wikipedia baseline summaries. Summaries generated using dependency patterns also lead to more readable summaries than those generated without dependency patterns.
Ahmet Aker, Robert J. Gaizauskas
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors Ahmet Aker, Robert J. Gaizauskas
Comments (0)
books