2010 · 85 citations · 20 references
ComputingComputer ScienceComputer VisionGeospatial Artificial IntelligenceNatural Language ProcessingDocument Image AnalysisDocument RepresentationGeospatial Natural Language ProcessingLanguage ModelingLanguage ModelsText SummarizationCaptioningContextual SummarizationDependency RepresentationImage CaptioningImage-text CorporaNeural Text SummarizationVisual Scene Description
This paper presents a novel approach to automatic captioning of geo-tagged images by summarizing multiple web-documents that contain information re-lated to an image’s location. The summa-rizer is biased by dependency pattern mod-els towards sentences which contain fea-tures typically provided for different scene types such as those of churches, bridges, etc. Our results show that summaries bi-ased by dependency pattern models lead to significantly higher ROUGE scores than both n-gram language models reported in previous work and also Wikipedia base-line summaries. Summaries generated us-ing dependency patterns also lead to more readable summaries than those generated without dependency patterns. 1
20
ROUGE: A Package for Automatic Evaluation of Summaries
Chin-Yew Lin · 2004 · 8.3K citations
Dependency tree kernels for relation extraction
Aron Culotta, Jeffrey Sorensen · 2004 · 831 citations · Full text
Applied Physics Letters · 2000 · 641 citations · Full text
A general language model for information retrieval
Fei Song, W. Bruce Croft · 1999 · 549 citations · Full text