TL;DR
Sangrahaka is a versatile web-based tool that facilitates entity and relationship annotation from text, constructs knowledge graphs, and enables natural language querying, adaptable for different languages and specific corpus needs.
Contribution
It introduces a customizable, user-friendly, and efficient annotation and querying framework for knowledge graphs, with open-source availability and demonstrated applicability in real tasks.
Findings
Supports language and corpus agnostic annotation
Provides fast and fault-tolerant performance
Demonstrated in two annotation tasks
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
