BriefGPT.xyz
Oct, 2016
堆叠残差LSTM网络的神经释义生成
Neural Paraphrase Generation with Stacked Residual LSTM Networks
HTML
PDF
Aaditya Prakash, Sadid A. Hasan, Kathy Lee, Vivek Datla, Ashequl Qadir...
TL;DR
该论文提出了一种用于生成释义的新型神经方法，其主要贡献是在残差LSTM网络中增加残差连接，有助于训练深度LSTM网络，并在三个不同的数据集上进行了评估，结果表明，这种方法优于其他深度学习模型。
Abstract
In this paper, we propose a novel
neural approach
for
paraphrase generation
. Conventional para- phrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machi
→