#Paper Reading# Neural Extractive Summarization with Side Information
来源:互联网 发布:电子图书数据库读秀 编辑:程序博客网 时间:2024/05/19 16:33
论文题目:Neural Extractive Summarization with Side Information
论文地址:https://arxiv.org/abs/1704.04530
论文发表于:arXiv(preprint) 2017
论文大体内容:
这篇通过增加side information(title, image caption)到单文档抽取式自动文本摘要中,使用层次式的document encoder和attention-based extractor的方法,在覆盖的信息量以及流畅性上面比没加side information的方式有了明显的提升。
1、本文关注点在于单文档,extraction式摘要;
2、抽取句子的方式是:按句子顺序,每个句子二分类,判断是否要加入摘要中;
3、模型结构图,包含3个组件:
①CNN sentence encoder;
②RNN document encoder;
③RNN(attention-based) sentence extractor
4、CNN sentence encoder(单层CNN)
①使用word2vec训练training set中的words,得到每个word的200维向量;
②1层的卷积+池化,得到sentence的embedding;
5、RNN document encoder
①使用LSTM的RNN;
②document的句子按逆序输入,防止漏掉前几个句子的作用;
6、RNN(attention-based) sentence extractor
①输入为sentence+side information
②输出为每个句子0/1,代表是否抽取该句子作为摘要;
实验
7、Dataset:CNN dataset(CNN articles),90K的training set,1220个validset,1093个testset;
8、Side information包括title,image caption,first sentence;
9、Baseline:
①LEAD-3:直接选择前3个句子作为摘要结果;
②POINTER-NET:没有用side information,但是使用了attention机制;
③SEQ2SEQ:a simple sequential encoder-decoder model which does not
use any side information;
10、评测标准:ROUGE
11、Side information的选择,发现选择title+caption能达到最好的效果
12、文摘截取长度对比
13、人工评测结果(选择20篇testset的文档,请5个人进行人工评估)
以上均为个人见解,因本人水平有限,如发现有所错漏,敬请指出,谢谢!
- #Paper Reading# Neural Extractive Summarization with Side Information
- #Paper Reading# Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
- #Paper Reading# SummaRuNNer: A RNN based Sequence Model for Extractive Summarization of Documents
- #Paper Reading# A Neural Attention Model for Abstractive Sentence Summarization
- #Paper Reading# Recent Advances in Document Summarization
- #Paper Reading# Manifold-Ranking Based Topic-Focused Multi-Document Summarization
- Extractive Summarization using Continuous Vector Space Models
- Abstractive Document Summarization with a Graph-Based Attentional Neural Model
- #Paper Reading# Multi-document Summarization Based on Cluster Using Non-negative Matrix
- #Paper Reading# Multi-Document Summarization via Sentence-Level Semantic Analysis and SMF
- Paper Reading
- Paper Reading
- Paper-Reading
- Ranking with Recursive Neural Networks and Its Application to Multi-document Summarization
- Paper Reading 1 - Playing Atari with Deep Reinforcement Learning
- Paper Reading 3:Continuous control with Deep Reinforcement Learning
- Paper Reading:Spatial Transformer Networks(with code explanation)
- Paper Reading:Spatial Transformer Networks(with code explanation)
- 移动端性能监控方案Hertz
- 易编远航第二期-三套网页游戏初接触
- 页面切换动画效果3
- 【企动力 “信“为本】华胜信泰ToprowDB-企业数据信息管理的神兵利器
- Spring中@Resource、@Autowired、@Qualifier的注解注入及区别
- #Paper Reading# Neural Extractive Summarization with Side Information
- 移动客户端与后台通信方式三
- 小例子,C#开发之kinect体感交互设备英文语音识别
- 一款开源的Android极客应用(持续更新)
- Git 常用命令整理
- 数组去重和冒泡排序
- 微信小程序UI代码书写范例
- curl工具介绍和常用命令
- oracle10 RAC节点添加过程