Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervis...
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
Jan Moringen, Sven Wachsmuth, Sven J. Dickinson, S...
We develop a mixture-based approach to robust density modeling and outlier detection for experimental multivariate data that includes measurement error information. Our model is d...
Reliable indexing of documents having seal instances can be achieved by recognizing seal information. This paper presents a novel approach for detecting and classifying such multi...
This paper addresses the problem of mining named entity translations from comparable corpora, specifically, mining English and Chinese named entity translation. We first observe...
Jinhan Kim, Long Jiang, Seung-won Hwang, Young-In ...