论文阅读 | Abstractive Sentence Summarization with Attentive Recurrent Neural Networks

最新推荐文章于 2022-03-31 18:24:26 发布

Shannon333

最新推荐文章于 2022-03-31 18:24:26 发布

阅读量812

点赞数

CC 4.0 BY-SA版权

分类专栏：论文阅读

本文链接：https://blog.youkuaiyun.com/qq_35924276/article/details/83959065

论文阅读专栏收录该内容

2 篇文章

订阅专栏

提出了一种基于条件递归神经网络的摘要生成方法，该模型通过卷积注意力机制聚焦于输入句子的关键部分，实现高质量的句子摘要生成。实验表明，此方法在Gigaword语料库和DUC-2004任务中表现出色。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Abstractive Sentence Summarization with Attentive Recurrent Neural Networks

摘要

Abstractive Sentence Summarization generates a shorter version of a given sentence while attempting to preserve its meaning.

We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence. （我们将介绍一种条件递归神经网络，其用来生成输入句子的摘要）

The conditioning is provided by a novel convolutional attention-based encoder which ensures that the decoder focuses on the appropriate input words at each step of generation. （使用一种conditional RNN来生成摘要，该条件是卷积注意力模型（convolutional attention-based encoder），用来确保每一步生成词的时候都可以聚焦到合适的输入上。）

Our model relies only on learned features and is easy to train in an end-to-end fashion on large data sets. （模型仅仅依赖于学习到的features，并且很容易在大规模数据上进行end2end式训练）

Our experiments show that the model significantly outperforms the recently proposed state-of-the-art method on the Gigaword corpus while performing competitively on the DUC-2004 shared task.（在Gigaword语料上和DUC-2004任务中取得了更好的效果。）