This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
sequence_to_sequence [2017/04/10 19:48] external edit
sequence_to_sequence [2018/10/20 13:33]
Line 122: Line 122:
 https://​arxiv.org/​pdf/​1704.02312v1.pdf A Constrained Sequence-to-Sequence https://​arxiv.org/​pdf/​1704.02312v1.pdf A Constrained Sequence-to-Sequence
 Neural Model for Sentence Simplification ​ Neural Model for Sentence Simplification ​
 +https://​arxiv.org/​pdf/​1810.01218v1.pdf AlphaSeq: Sequence Discovery with Deep
 +Reinforcement Learning
 +https://​github.com/​locuslab/​trellisnet ​
 +This allows trellis networks to serve as bridge between recurrent and convolutional architectures,​ benefitting from algorithmic and architectural techniques developed in either context. We leverage these relationships to design high-performing trellis networks that absorb ideas from both architectural families.