NLP as Services

Project Title

NLP as Services

Project Area of Specialization Artificial IntelligenceProject Summary

NLP as a service is the main functional aspect of this project that could be used as an API in multiple systems such as ERPS.

            Big information systems contain various circumstances of weak information maintenance through which they need some annotation tools to process that data.

            To help the text analysis problems along with efficient and flexible support system in decision making process and processing huge amount of data for multiple modules inside the big systems, there is a need of natural language processing system that could be used as an API in the System. 

Named-entity recognition (NER) (also known as entity identification, entity chunking and entity extraction) is a subtask of information extraction that seeks to locate and classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc.. 

Keyword extraction is tasked with the automatic identification of terms that best describe the subject of a document.

Key phrases, key terms, key segments or just keywords are the terminology which is used for defining the terms that represent the most relevant information contained in the document. Although the terminology is different, function is the same: characterization of the topic discussed in a document. Keyword extraction task is important problem in Text Mining, Information Retrieval and Natural Language Processing. i.e. If the domain of a text as extracted by the Entity recognition is Hospital then it will extract all the keywords that are under the umbrella of Hospital i.e. Doctor, medicine, Operation, patient.Nowadays the development of information systems and technology, businesses and other organization’s databases depend on the organization's purpose and structure of various types of data.Raw data is not processed as long as a meaningless pile of data stored in databases.Big information systems contain various circumstances of weak information maintenance through which they need some annotation tools to process that data.NLP as a service is the main functional aspect.NLP will be use as an API in multiple systems such as ERPS.

Most research on NER systems has been structured as taking an unannotated block of text, such as this one

Project Objectives

  The main objective of NaaS is to build a system that should process the raw data and extract the useful information from the given domain by using the Formal algorithms and software engineering processes.NLP will be use as an API in multiple systems such as ERPS. To build a system that should process the raw data and extract the useful information from the given domain. To use the Formal algorithms and software engineering processes. To solve text analysis problems along with efficient and flexible support system. To  make decisions in process and processing huge amount of data for multiple modules.

Project Implementation Method

Named-entity recognition (NER) (also known as entity identification, entity chunking and entity extraction) is a subtask of information extraction that seeks to locate and classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc.

Most research on NER systems has been structured as taking an unannotated block of text, such as this one

Keyword extraction is tasked with the automatic identification of terms that best describe the subject of a document.

Key phrases, key terms, key segments or just keywords are the terminology which is used for defining the terms that represent the most relevant information contained in the document. Although the terminology is different, function is the same: characterization of the topic discussed in a document. Keyword extraction task is important problem in Text Mining, Information Retrieval and Natural Language Processing. i.e. If the domain of a text as extracted by the Entity recognition is Hospital then it will extract all the keywords that are under the umbrella of Hospital i.e. Doctor, medicine, Operation, patient.

A relationship extraction task requires the detection and classification of semantic relationship mentions within a set of artefacts, typically from text or XML documents. The task is very similar to that of information extraction (IE), but IE additionally requires the removal of repeated relations (disambiguation) and generally refers to the extraction of many different relationships.

            In the sentence, “This phone has a nice camera but it`s sound quality is worst”, the relation between nice and camera is nsubj(noun, subject) and the relation between phone and The is det(detriment).

Benefits of the Project

  The main objective of NaaS is to build a system that should process the raw data and extract the useful information from the given domain by using the Formal algorithms and software engineering processes.NLP will be use as an API in multiple systems such as ERPS.

Big information systems contain various circumstances of weak information maintenance through which they need some annotation tools to process that data.NLP as a service is the main functional aspect.NLP will be use as an API in multiple systems such as ERPS.

Most research on NER systems has been structured as taking an unannotated block of text, such as this one

Technical Details of Final Deliverable

Thesystem is meant to be an API that would be use in the big data systems as a jar file for processing the data.

Entity Extraction:  is a subtask of information extraction that seeks to locate and classify named entities in the text.

  Keyword Extraction: keyword extraction is tasked with the automatic identification of terms that best describe the subject of a document.

Relation Extraction: A relationship extraction task requires the detection and classification  of semantic relationship within a set of artifacts typically from text or XML documents.

Concept Tagging: Concept Tagging involves streaming your text against a dictionary of concepts, drawn from an ontology that describes your domain.

Sentiment Analysis: Sentiment analysis (sometimes known as opinion mining or emotion AI) refers to the use of natural language processing, text analysis, computational linguistics.

Text Analytics: Text mining also referred to as text data mining, roughly equivalent text analytics, is the process of deriving high quality information from text.

Data Visualization: NLP as a service would use web user interface as the front end of the application for the processing of the information.

Stanford CoreNLP

Stanford Parser

Stanford NER

Stanford POS Tagger

NLTK

python 3.6

 pycharm

 mongodb

 bootstrap

flask

Final Deliverable of the Project HW/SW integrated systemType of Industry IT Technologies Artificial Intelligence(AI)Sustainable Development Goals Quality EducationRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	75
NLP Technologies	Equipment	5	15	75