Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular structures. How to generate both syntactically and semantically correct data still remains largely an open problem. Inspired by the theory of compiler where t...

An approach to joint equalization and decoding for vector quantization over a Gaussian channel with intersymbol interference is presented. The decoder is based on a Hadamard transform representation of the vector quantizer. This gives the decoder a structure that allows the decoding to be based on estimates of the transmitted bits in an efficient manner. The decoder is soft in the sense that so...

In this paper, we evaluate several techniques for generating and optimizing high speed software decoders. We begin by presenting the early stages of a new instruction set description language named ‘Rosetta’. We use specifications written in this language to automatically generate a number of different software decoders. We explore heuristics for generating decoder trees, particularly with rega...

In this paper, we study and analyze the computational complexity of a software-based H.264/AVC baseline profile decoder. Our analysis is based on determining the number of basic computational operations required by a decoder to perform the key decoding subfunctions. The frequency of use of each of the required decoding subfunctions is empirically derived using bitstreams generated from two diff...

This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows significant improvement over a strong RNN-based encoder-decoder baseline and ac...