Currently the unified semantic role labeling (SRL) that achieves predicate identification and argument in an end-to-end manner has received growing interests. Recent works show leveraging syntax knowledge significantly enhances SRL performances. In this paper, we investigate a novel framework based on sequence-to-sequence architecture with double enhancement both encoder decoder sides. side, pr...

Consider the rate-distortion problem, in which a helper sends a common limited-rate message both to the encoder and decoder based on side information at its disposal. We characterize the region of achievable rates and distortions for this problem. We derive these regions explicitly for binary doubly symmetric sources with Hamming distortion, and for Gaussian sources with square error distortion...

Error control decoders are widely used in communication applications. Analog CMOS implementations of error control decoders may outperform digital implementations in portable applications where power is limited. However, there have been little circuit level analyses of analog decoder designs. This dissertation covers the related analog circuits in the decoder design based on the extended (8, 4)...

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is a deep Convolutional Neural Network (CNN) based on the VGG network. The CTC network sits on top of the encoder and is jointly trained with the attention-base...