AUTOMATIC METADATA HARVESTING FROM DIGITAL CONTENT

摘要

Metadata Extraction s one of the predominant research fields in information retrieval. Metadata is used to references information resources. Most metadata extraction systems are still human intensive since they require expert decision to recognize relevant metadata but this is time consuming. However automatic metadata extraction techniques are developed but mostly works with structured format. We proposed a new approach to harvesting metadata from document using NLP. As NLP stands for Natural Language Processing work on natural language that human used in day today life.