Learn More
The problem of cross-modal retrieval, e.g., using a text query to search for images and vice-versa, is considered in this paper. A novel model involving correspondence autoencoder (Corr-AE) is proposed here for solving this problem. The model is constructed by correlating hidden representations of two uni-modal autoencoders. A novel optimal objective, which(More)
The ICML 2013 Workshop on Challenges in Representation Learning(1) focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of(More)
Stripe rust, caused by Puccinia striiformis f. sp. tritici (Pst), is one of the most destructive diseases of wheat. Here we report a 110-Mb draft sequence of Pst isolate CY32, obtained using a 'fosmid-to-fosmid' strategy, to better understand its race evolution and pathogenesis. The Pst genome is highly heterozygous and contains 25,288 protein-coding genes.(More)
Person, location and organization have been always mentioned as a bottleneck of a named entity recognition (NER) system. Automatic recognition of Chinese organization name is the most difficult problem in NER tasks. This paper presents a new approach of Chinese organization name recognition based on cascaded conditional random fields. In the proposed(More)
BACKGROUND Stripe rust of wheat, caused by Puccinia striiformis f. sp. tritici (Pst), is one of the most important diseases of wheat worldwide. Due to special features of hexaploid wheat with large and complex genome and difficulties for transformation, and of Pst without sexual reproduction and hard to culture on media, the use of most genetic and(More)
BACKGROUND Puccinia striiformis f. sp. tritici is a fungal pathogen causing stripe rust, one of the most important wheat diseases worldwide. The fungus is strictly biotrophic and thus, completely dependent on living host cells for its reproduction, which makes it difficult to study genes of the pathogen. In spite of its economic importance, little is known(More)
Our proposed method is to use a Hidden Markov Model-based word segmenter and a Support Vector Machine-based chunker for Chinese word segmentation. Firstly, input sentences are analyzed by the Hidden Markov Model-based word segmenter. The word seg-menter produces n-best word candidates together with some class information and confidence measures. Secondly,(More)
Chinese Pinyin-to-character conversion is a key technology in Chinese Pinyin input system. In sentence based Pinyin-to-character conversion, segmentation of Pinyin string has important influence on performance of Pinyin-to-character conversion. There are lots of ambiguities in segmentation of Pinyin string. This paper classifies them into overlap and(More)