摘要提取

Introduction##

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.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.

After trying many methods of summarizations, we decided to do that by ourselves. And we have submitted a paper to CIKM 2017— Structured Text Summarization via Open Domain Information Extraction.

In this paper, 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:

Harvard University
• is a private Ivy League research university in Cam- bridge, Massachusetts
• is the United States’ oldest institution of higher learning

Approach##

image.png

detailed implementation of these three step can be show on our paper.

User Interface##

search for the text:

image.png

show the summarization:

image.png