Lasse Espeholt

Teaching Machines to Read and Comprehend

2015 · arXiv (Cornell University)

Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until …

Neural Machine Translation in Linear Time

2016 · arXiv (Cornell University)

We present a novel neural network for processing sequences. The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the …