Sangrahaka: A Tool for Annotating and Querying Knowledge Graphs
This tool addresses the need for efficient and user-friendly knowledge graph creation and querying, particularly for researchers and practitioners working with text corpora, though it is incremental as it builds on existing annotation and KG methods.
The authors developed Sangrahaka, a web-based tool for annotating entities and relationships from text to build knowledge graphs and query them using natural language templates, with features like speed, customization, and fault tolerance.
In this work, we present a web-based annotation and querying tool Sangrahaka. It annotates entities and relationships from text corpora and constructs a knowledge graph (KG). The KG is queried using templatized natural language queries. The application is language and corpus agnostic, but can be tuned for special needs of a specific language or a corpus. A customized version of the framework has been used in two annotation tasks. The application is available for download and installation. Besides having a user-friendly interface, it is fast, supports customization, and is fault tolerant on both client and server side. The code is available at https://github.com/hrishikeshrt/sangrahaka and the presentation with a demo is available at https://youtu.be/nw9GFLVZMMo.