Keyword extraction and summarization from unstructured text: A case study with open data from legal domain

Abstract

Information Extraction (IE) is an important and crucial task in the world of web and open data. IE is achieved using Natural language Processing (NLP). There are various techniques used for extraction of information, however coming up with useful and meaningful information is the most important task. Many search engines rely heavily on IE. This paper focuses on entity extraction of named entities from natural language and converting them into knowledge graph of triples. The goal is to answer two types of queries (i) Keyword search that returns exact information; (ii) Summarization of a keyword in question. A case study using open data from legal domain is presented.