Automatic Recapitulation of Text Document
semanticscholar(2018)
摘要
1,2,3,4 Department of Computer Technology, Yeshwantrao Chavan College of Engineering, Nagpur, Maharashtra, India --------------------------------------------------------------------------------***--------------------------------------------------------------------------------Abstract The information over the internet is increasing very rapidly making it difficult to take out concise information. Users have to read the whole document to determine that the given document is relevant or not. Thus it is necessary to build a system that could present human quality summaries. Automatic Recapitulation of Text is a tool to reduce the document from its original size by presenting the main points in a concise form. Recapitulation process involves interpretation, transformation and generation. To generate an appropriate summary, the input text is pre-processed which involves tokenization, stop-words removal and stemming. The appropriate features are extracted from the input data, tf-idf values for each word are computed and all the pre-processed input is transformed into a tf-idf matrix. In the proposed extractive-based approach sentences are given scores based on different feature and sentences with higher rating are selected for meaningful summary. It uses various Natural Language processing approaches for information retrieval. The proposed approach states the methodology for generating the relevant summary using WordNet.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要