Publication

Abstract : The core concept of this project revolves around constructing a knowledge graph from any given text document, employing advanced data science techniques. This chapter delves into the significance of structurally arranging data and information. The methodology encompasses several key steps including sentence segmentation, entity extraction, and relation extraction, culminating in the creation of a Knowledge Graph from Text Data. In this project, the main focus is on identifying three relations. Song_composedby, Screenplay_Writtenby, and Movie_Releasedin. We created a corpus of 4300 sentences from 500 articles and recognised movie details in Wikipedia to evaluate the model. These extracted relations are manually checked and created the knowledge graph. This knowledge graph serves as a structured and lucid representation of the underlying text, providing clear access to the desired information.The structured knowledge graph enables precise data retrieval, enhancing overall accessibility and usability.