Fast Evaluation of Connectionist Language Models

19 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, background): “There has been a long history [19, 26, 27, 433] of using (shallow) feed-forward neural networks in LMs, called the NNLM.”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “There has been a long history (e.g., [196, 197]) of using (shallow) neural networks in LM – an important component in speech recognition, machine translation, text information retrieval, and in natural language processing.”
Neural network language models for off-line handwriting recognition (2014, methodology): “(7)), we have used an adapted version of [42] which consists of pre-computing the M softmax normalization factors most probably needed during decoding.”