Introduction for Structured Text Summarization
来源:互联网 发布:龙门式加工中心编程 编辑:程序博客网 时间:2024/06/11 04:07
Given the dramatic growth of digital content, new solutions are needed for us to be able to get a quick overview of pertinent information without being inundated by irrelevant details. While there has been ample research on automatic summarization methods, summaries may still be somewhat convoluted and hard to absorb. In our system, we propose the novel task of structured text summarization, which we address by combining ranking techniques with open information extraction. This method yields an uncluttered, more easily digestible overview of key insights from a text.
In light of the staggering growth of digital content now vying for our attention at any given point in time, reading every long article that we come across in full detail is no longer practical. For instance, having assumed a leadership role at a multinational company, a person will likely lack the time for an in-depth reading of a long, detailed article recounting, say, the political deliberations surrounding the possible introduction of new labor laws in Thailand. Instead, such a person may just wish to receive a very concise overview of the proposals being discussed. While executives may be able to rely on consultants or staff to provide brief executive summaries, it would be helpful to have innovative new technological solutions to this problem. These could enable us to more quickly get an overview of the key information in a long article without being inundated by irrelevant details.
Past research along these lines has focused on the task of automatic summarization, which compresses a given text to distill a shorter version. While this may go a long way, the resulting summaries may still be poorly organized and convoluted.
In our system , we propose the novel task of structured text summarization,which seeks to produce structured lists of textual items that are less cluttered and constitute more easily digestible overviews of key insights from a text. We address this task by combining salience-based ranking techniques to identify important content with methods based on open domain information extraction (Open IE) to convert sentences to a structured form, from which the main thoughts are more easily discernible.
Consider the following input sentences:
Harvard University is a private Ivy League research university in Cambridge, Massachusetts. Harvard is the United States’ oldest institution of higher learning.
Our system combines and converts these two sentences into a structured form as follows:
- Introduction for Structured Text Summarization
- 论文读书笔记-automatic text summarization for annotating images
- RBM-An approach for text summarization using deep learning algorithm
- Text Summarization 综述
- 【论文笔记】Deep Structured Output Learning for Unconstrained Text Recognition
- introduction with a Search Enghine for Text
- Bigtable: A Distributed Storage System for Structured Data : part1 Abstract and Introduction
- A Survey on Automatic Text Summarization
- Taming Recurrent Neural Networks for Better Summarization
- A Deep Reinforced Model for Abstractive Summarization
- Framework of Automatic Text Summarization Using Reinforcement Learning
- #Paper Reading# A Neural Attention Model for Abstractive Sentence Summarization
- [EMNLP2015]A Neural Attention Model for Sentence Summarization
- SEH( Structured Exception Handler) for Windows
- Week2-3Text similarity:introduction
- 论文笔记 《Information Extraction:Distrilling Structured Data from Unstructured Text》
- Introduction for localization testing
- simple introduction for bash
- 阿里社招面试感悟----一名3年工作经验的程序员应该具备的技能
- ffmpeg中的ff_check_interrupt
- linux下安装Memcached
- cpp-netlib笔记二:实现http文件服务功能
- Idea最优方案
- Introduction for Structured Text Summarization
- javascript中call和apply的区别
- Ruby中 split 方法
- Android中实现ScrollView的滚动事件监听
- IOS 安装 ffmpeg
- 5款开源的Dashboard工具
- caffe+vs2015+anaconda,Python2.7+无GPU安装问题
- Java @Retention注解
- 趣探 Mach-O:文件格式分析