Paper Reading - Sequence to Sequence Learning with Neural Networks ( NIPS 2014 )-优快云博客

本文介绍了一种使用神经网络进行序列到序列学习的方法，采用编码器-解码器模型，通过多层LSTM实现从输入序列到目标序列的转换。实验表明，对输入序列进行反转能显著提高模型性能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Link of the Paper: https://arxiv.org/pdf/1409.3215.pdf

Main Points:

Encoder-Decoder Model: Input sequence -> A vector of a fixed dimensionality -> Target sequence.
A multilayered LSTM: The LSTM did not have difficulty on long sentences. Deep LSTMs significantly outperformed shallow LSTMs.
Reverse Input: Better performance. While the authors do not have a complete explanation to this phenomenon, they believe that it is caused by the introduction of many short term dependencies to the dataset. LSTMs trained on reversed source sentences did much better on long sentences than LSTMs trained on the raw source sentences, which suggests that reversing the input sentences results in LSTMs with better memory utilization.

Other Key Points:

A significant limitation: Despite their flexibility and power, DNNs can only be applied to problems whose inputs and targets can be sensibly encoded with vectors of fixed dimensionality.

posted on 2018-08-09 10:06 LZ_Jaja 阅读( ...) 评论( ...) 编辑收藏

转载于:https://www.cnblogs.com/zlian2016/p/9447209.html