Agricultural Knowledge Extraction from Text Sources Using a Distributed MapReduce Cluster

Extracting and accessing knowledge in a Knowledge Base is a crucial task. Documents must be computationally understood and transformed into accessible knowledge. Specifically, the farming industry has a notable importance due to the wide variety of information from text documents that need to be int...

Full description

Saved in:
Bibliographic Details
Main Authors: Gomez-Perez, Pablo, Trong Nhan Phan, Kueng, Josef
Format: Conference Proceeding
Language:English
Subjects:
Chemicals
Classification algorithms
Engines
Full-text search
Hadoop
Industries
Java
Knowledge based systems
Knowledge Extraction
MapReduce
Natural language processing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Extracting and accessing knowledge in a Knowledge Base is a crucial task. Documents must be computationally understood and transformed into accessible knowledge. Specifically, the farming industry has a notable importance due to the wide variety of information from text documents that need to be interpreted, often by a human. These documents, often relates to regulations, chemicals, seeds and fertilizers among others. Moreover, automatize document processing increases its importance in areas like the European Union with its language and regulation differences which increases the complexity of farming in general. Our approach aims to help users by means of providing a scalable system using a distributed MapReduce document cluster to process all this information to provide an accessible way to this knowledge thereafter.
ISSN:2378-3915
DOI:10.1109/DEXA.2016.022