PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

时间 2021-01-02

标签 NLP 繁體版

原文原文链接

就在这几天微软发布了一款参数量多达170亿的史上最大的自然语言生成模型 Turing-NLG，在多种语言模型基准上均实现了SOTA。值得关注的是Turing-NLG在文本摘要上的表现，由于它已经非常善于理解文本了，因此不需要太多的配对数据就可以实现比已有模型更好的效果。从Facebook的BART、Google的PEGASUS到今天Microsoft的Truing-NLG，越来越大的预训练数据

>>阅读原文<<

1. A Deep Reinforced Model for Abstractive Summarization
2. #Paper Reading# Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
3. Fast Abstractive SUmmarization with Reinforce-Selected Sentence Rewriting
4. Deep Communicating Agents for Abstractive Summarization论文分享
5. PEGASUS
6. #Paper Reading# A Neural Attention Model for Abstractive Sentence Summarization
7. Self-Attention Guided Copy Mechanism for Abstractive Summarization---ACL 2020
8. 多标签分类：Global Encoding for Abstractive Summarization
9. 【读】seq2seq——（2）Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
10. NLG简要调研(data2text+(Abstractive) Summarization)
更多相关文章...
• Swift for 循环 - Swift 教程
• Scala for循环 - Scala教程
• 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
• 算法总结-股票买卖

最新文章

1. Window下Ribbit MQ安装
2. Linux下Redis安装及集群搭建
3. shiny搭建网站填坑战略
4. Mysql8.0.22安装与配置详细教程
5. Hadoop安装及配置
6. Python爬虫初学笔记
7. 部署LVS-Keepalived高可用集群
8. keepalived+mysql高可用集群
9. jenkins 公钥配置
10. HA实用详解

本站公众号

欢迎关注本站公众号,获取更多信息

1. A Deep Reinforced Model for Abstractive Summarization
2. #Paper Reading# Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
3. Fast Abstractive SUmmarization with Reinforce-Selected Sentence Rewriting
4. Deep Communicating Agents for Abstractive Summarization论文分享
5. PEGASUS
6. #Paper Reading# A Neural Attention Model for Abstractive Sentence Summarization
7. Self-Attention Guided Copy Mechanism for Abstractive Summarization---ACL 2020
8. 多标签分类：Global Encoding for Abstractive Summarization
9. 【读】seq2seq——（2）Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
10. NLG简要调研(data2text+(Abstractive) Summarization)

>>更多相关文章<<