• Deval S Goda
• Prof. Dulari A Bosamiya

Metadata Extraction is one of the leading research fields in Information Retrieval. Metadata helps providing access to information resources. It makes the discovery and organization of resources substantially easy. The manual collection of such metadata is a tiresome, at times inaccurate and time consuming process. Moreover, the fastest rate at which digital contents are produced will ultimately make it impossible to rely on manual methods. Some automated techniques has to be there for the above said metadata gaining. This paper describes some of the available techniques like Metadata extraction with cue model or by TF*PDF algorithm or with the help of support vector machines. One of them is the extraction using a Keyphrase Extraction tool (KET), while the other automatically extracts keywords from web sources.

Metadata, Extraction, Information Retrieval

"Review of Various Techniques of Automatic Metadata Extraction from Digital Documents", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.1, Issue 7, page no.660-664, December-2014, Available :http://www.jetir.org/papers/JETIR1407014.pdf

"Review of Various Techniques of Automatic Metadata Extraction from Digital Documents", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.1, Issue 7, page no. pp660-664, December-2014, Available at : http://www.jetir.org/papers/JETIR1407014.pdf