Lexical Text Simplification Using WordNet
Autor: | Vishal Dolase, Kajol Agrawal, Yogesh Rajmane, Mrunmayee Tambe, Debabrata Swain, Preeti Ballal |
---|---|
Rok vydání: | 2019 |
Předmět: |
Distributed Computing Environment
Data collection Computer science Text simplification business.industry media_common.quotation_subject Lexical analysis WordNet computer.software_genre Reading (process) The Internet Artificial intelligence business computer Natural language Natural language processing media_common |
Zdroj: | Communications in Computer and Information Science ISBN: 9789811399411 |
DOI: | 10.1007/978-981-13-9942-8_11 |
Popis: | Internet is distributed environment and hence, huge amount of information is available on it. People use internet to access the information on the web. While referring to any information people face difficulty to understand the complex sentences and words used related to technology and science. Technical and scientific words are mostly found in research papers, medical reports, newspapers and other reading material. Text simplification is a technique used to automatically transform complicated text into simpler form. In the proposed system an efficient text simplification technique has been developed using word net model available in the Natural Language toolkit (NLTK). The dataset used for experimentation is collected through a random survey from web sources. Here, the proposed system is divided into 3 phases. In the first phase data collection and pre-processing has been performed. In second phase complex words are identified and in the 3rd phase replacement of complex words with their simple synonyms is being done. The performance of the system has been analyzed by user review to accuracy of 87%. |
Databáze: | OpenAIRE |
Externí odkaz: |