期刊名称：International Journal of Computers and Communications
印刷版ISSN：2074-1294
出版年度：2014
卷号：8
页码：67-76
出版社：University Press
摘要：We propose semantics and associated Natural Language Understanding (NLU) based approach to address the key problems of big data. Our approach use human Brain-Like and Brain-Inspired algorithms as humans can very effectively retrieve knowledge from data as well as can significantly compress the data by using the semantics of the information. This is true for both unstructured and structured data which are growing very fast - already exceeding the exabyte range. Unstructured data, however, dominates structured data with a wide margin. There are multiple problems with big data including storage, search, transfer, sharing, analysis, processing, viewing, and deriving meaning / semantics. Such problems are mainly due to the 4 Vs i.e. Volume, Velocity, Variety and Variability. All these problems can be addressed well when the data can be highly compressed and meaning of the data can be converted to knowledge. We propose to use Semantic Engine using Brain-Like Approach (SEBLA) to convert data to knowledge and also to compress it; thus addresses the Big Data problems in an effective way. SEBLA provides “Natural Semantics” i.e. semantics similar to what humans use. The main theme in SEBLA is to use each word as object with all important features, most importantly the semantics. In our human natural language based communication, we understand the meaning of every word even when it is standalone i.e. without any context. Sometimes a word may have multiple meanings which get resolved with the context in a sentence. The next main theme is to use the semantics of each word to develop the meaning of a sentence as we do in our natural language understanding as human. Similarly, the semantics of sentences are used to derive the semantics or meaning of a paragraph. The 3rd main theme is to use natural semantics as opposed to existing “mechanical semantics” of Predicate logic or Ontology or the like. All these together can achieve summarization and draw inference i.e. finding useful information or converting data to knowledge, at least to first degree. These have numerous applications (e.g. Business Intelligence, Analytics, Document Summarization, and Document Analysis). There are other types of key applications using the semantic capability of SEBLA including Intelligent Information Retrieval, Intelligent Search, Question and Answer System, and Intelligent Language Translation. We have presented a few such applications.
关键词：Big Data; Unstructured Data; Natural Language;Understanding (NLU); Semantics; Artificial Intelligence; Data;Mining; Knowledge Discovery; Data Science; Interpreting Data;Internet; Intelligent Internet; Question & Answer System; Intelligent;Agent; Machine Learning; Predictive Analysis; Business Intelligence;High Value Business Problems; Information Technology.
