This paper addresses the problem of dynamic model parameter selection for loglinear model based statistical machine translation (SMT) systems. In this work, we propose a principle...
This paper makes three significant extensions to a noisy channel speller designed for standard written text to target the challenging domain of search queries. First, the noisy ch...
Jianfeng Gao, Xiaolong Li, Daniel Micol, Chris Qui...
Update of acoustic and language models is vital to maintain performance of automatic speech recognition (ASR) systems. To alleviate efforts for updating models, we propose a "...
Yuya Akita, Masato Mimura, Graham Neubig, Tatsuya ...
This paper investigates the combination of different neural network topologies for probabilistic feature extraction. On one hand, a five-layer neural network used in bottle neck f...
The complicated interactions among tasks lead to iterations in product design and development. To maintain the market share, enterprises should effectively manage their product de...