Current Proceedings on Technology

Yazarlar: Farhad Soleimanian Gharehchopogh, Zeinab Abbasi Khalifehlou

Konular:-

Anahtar Kelimeler:Information Extraction,Text Mining,Knowledge Discovery,Atural Language Processing, 

Özet:   In today’s word, information had been stored in organizations is as unstructured data. Unstructured models include Unstructured Data (UD) like text files in warehouses or databases.UD specify information from data hoard in archive forms in data warehouses or text files. Also, Text Mining (TM) and Natural Language Processing (NLP) are two sub-domains of Artificial Intelligence (AI) techniques using to extract information from UD. Thus, extraction and retrieval of conductive data will be fundamental work in semantic web districts that depend on the storage’s quality. Then, UD can be enriched and tagged to identifying ambiguities and relevant based methods. These techniques applied for facilitating search and exploring actions. In this study, we investigate TM, NLP and UD firstly; TM and natural language techniques used to detect knowledge as well as information extraction (IE) will review and discussed. Main scope of the paper is evaluation among of the TM versus NLP through appropriate relevant techniques.

---