Didier Bourigault Didier, R&D Director at Synomia and researcher at CNRS,
explains why he thinks unstructured data analysis is such an important issue
for Big Data analytics
In laboratories, researchers in Natural Language Processing, Artificial Intelligence and Text Mining develop sophisticated algorithms for automatic text processing. But these results do not pass the three tests of speed, adequate coverage, and robustness.
As part of our collaboration with CNRS, Synomia acquired a radically innovative textual analysis technology, the result of research that blew away the technological barriers that previously prevented the use of such tools in industrial and commercial contexts. This technology is based on a parsing algorithm. The parser used by Synomia identifies all syntactic relationships (subject, object, complement, epithet, attribute, etc...) in all sentences of the corpus under analysis. From these analyses, it builds a terminology network that reveals the conceptual structure of knowledge expressed in the corpus.
Unlike existing tools on the market that require users to program his their extraction rules, and therefore to already have a clear idea of what they are looking for, the Synomia parser allows users to discover the intrinsic content of the analyzed corpus without prejudice. Through this unique expertise, Synomia makes exploiting unstructured data accessible to all companies, and allows the Synomia Data Analyst to focus not on data collection but on its use and on the discovery of differentiating consumer insights.