22k citations · 22.8k across the 12 of their papers we have counts for
Showing cs.NEShow all
2 papers · 1 filter
cs.NE2016
Neural Associative Memory for Dual-Sequence Modeling
Dirk Weissenborn
Many important NLP problems can be posed as dual-sequence or sequence-to-sequence modeling tasks. Recent advances in building end-to-end neural architectures have been highly succe…
cs.NE2016★ 3 cited
MuFuRU: The Multi-Function Recurrent Unit
Dirk Weissenborn, Tim Rocktäschel
Recurrent neural networks such as the GRU and LSTM found wide adoption in natural language processing and achieve state-of-the-art results for many tasks. These models are characte…