IIIT-Delhi Institutional Repository

Knowledge graph construction from text

Show simple item record

dc.contributor.author Saini, Vipul
dc.contributor.author Mutharaju, V. Raghava (advisor)
dc.contributor.author Chakraborty, Tanmoy (advisor)
dc.date.accessioned 2021-05-25T09:00:34Z
dc.date.available 2021-05-25T09:00:34Z
dc.date.issued 2020-06-05
dc.identifier.uri http://repository.iiitd.edu.in/xmlui/handle/123456789/924
dc.description.abstract Knowledge graphs have become quite popular and their utility is increasing at a very fast rate. There exist numerous extensive knowledge graphs that contain information on a plethora of topics. With new information (referred to as entities) being put on the internet each passing day, it becomes necessary for knowledge graphs to include these novel entities dynamically. To retrieve information on these new topics, the graphs need to be up to date. In this paper, we propose a way to enrich the graph with new entities by connecting them to pre-existing entities with valid relations by taking into consideration the description of the new entity. We start by finding entities similar to the novel entity with the help of the description, followed by relation extraction and filtering, and finally perform link prediction on the obtained entities and their corresponding relations. We report the hits@10, precision and MRR for the new triples in our evaluation. en_US
dc.language.iso en_US en_US
dc.publisher IIIT-Delhi en_US
dc.subject (Knowledge Graph, Entity prediction, Link prediction, Graph Convolutional Networks, Document embedding, Knowledge Graph Embedding en_US
dc.title Knowledge graph construction from text en_US
dc.type Other en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Repository


Advanced Search

Browse

My Account