Yu-Yu Chou

Learn More
In this paper, we propose a semantic query expansion approach by extending the query-regularized mixture model to include latent topics and apply it to spoken documents. We also propose to use context feature vectors for spoken segments to train SVM models to enhance the posterior-weighted normalized term frequencies in lattices. Experiments on Mandarin(More)
Supervised approaches can learn a spoken document summarizer generating high-quality summaries using a set of training examples matched to the domain of target documents. However, preparing a sufficient number of in-domain training examples is expensive. In this paper we propose an approach for unsupervised domain adaptation for spoken document(More)
Conservation biologists have allocated an Indo-Burma biodiversity hotspot among 34 regions around the world especially rich in plants, animals, and other species (Myers et al., 2000). More than 13,500 different vascular plant species, of which 7000 are endemic, have been detected in this hotspot (Tordoff et al., 2012). Ninety years ago, the Russian(More)
  • 1