Natural Language Processing, otherwise known as computational linguistics, is the combination of machine learning, AI, and linguistics. By deriving advanced models for representing languages, such as treating language as a cooperative game between the speaker and the listener, NLP along with its more complex cousin NLU (Natural Language Understanding), the applications can be far-reaching and multifarious. E.g. by turning BI into a conversation with a chatbot, accessing information will be as easy as asking – ‘how have revenues changed over the last three-quarters?’ rather than knowing how to formulate specialized queries. Onometra has developed IP assets in areas of Pattern matching, Syntactically driven parsing and semantic grammar. Based on the requirements of our clients, we use advanced sentence classification techniques like, sentiment analysis, named entity recognition, disambiguation etc, on heterogenous and unstructured text, for:
Extracting entities – such as companies, people, dollar amounts, key initiatives, etc.
Categorizing content – positive or negative (e.g. sentiment analysis), by function, intention or purpose, or by industry or other categories for analytics and trending
Clustering content – to identify main topics of discourse and/or to discover new topics
Fact extraction – to fill databases with structured information for analysis, visualization, trending, or alerts
Relationship extraction – to fill out graph databases to explore real-world relationships