A Model for Document Retrieval Using Earth Mover Distance

Abstract

The recent rise in the amount of unstructured data in digital format has given rise to the use of natural language processing techniques to understand the data. Organizations have started recognizing the potential in the unstructured textual data. Data from the internet as well as from the organizations' internal repository can help them to gain more insight into the market. Information collected from such sources provides valuable decision-making probability for the organizations. Keyword-based search is the most helpful form of the document retrieval process. The paper discusses such processes used in the current scenario as well as propose a new form of technique to be used for the process of document retrieval.