Key phrase extraction system for agricultural documents

Abstract

Keywords play a vital role in extracting relevant and semantically related documents from a huge collection of various documents. Keywords represent the main topics covered in the document. But manual keyword extraction is a tedious and time-consuming process. Thus, there is a need for an automated keyword extraction system for easier extraction of relevant documents. In this paper, the focus is on agriculture-related documents. Agrovoc, an agriculture-based vocabulary that contains more than 35,000 concepts is used for extracting relevant keywords from the document. The proposed system extracts the relevant keywords from agricultural documents which are further used to extract relevant documents. Also, with the increasing number of documents on the Internet, the need for efficient storage for keywords with their corresponding documents is necessary. In the proposed system, a trie-based inverted index has been used for efficient storage and retrieval of keywords and the related documents.