This paper proposes a chunking strategy to detect unknown words in Chinese word segmentation. First, a raw sentence is pre-segmented into a sequence of word atoms 1 using a maximum...
We compare and contrast two different models for detecting sentence-like units in continuous speech. The first approach uses hidden Markov sequence models based on N-grams and max...
Yang Liu, Andreas Stolcke, Elizabeth Shriberg, Mar...
Abstract. This paper introduces a new similarity measure for multimodal image registration task. The measure is based on the generalized survival exponential entropy (GSEE) and mut...
We propose Laplace max-margin Markov networks (LapM3 N), and a general class of Bayesian M3 N (BM3 N) of which the LapM3 N is a special case with sparse structural bias, for robus...
We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...