Text2CausalGraph
By Seetha Gopalakrishna, Victor Z. Chen, Sreekar Nedunuri, Gus Hahn-Powell, Wenwen Dou, Wlodek Zadrozny
Text2CausalGraph is a web-based interface to detect, extract, deconstruct, and classify the causal insights (e.g., causes, links, outcomes) from unstructured textual documents. The machine reading is pretrained on a corpus of SEC 10K reports of S&P 65 financial companies.
Github Repo
https://github.com/GoPeaks-AI/text2causalgraph
See, also, US Patent Pending No. US20240185491A1 "Computer implemented method and system for integrative causal modeling and transfer"
Share this page via
GoPeaks has ended its commercial activities since April 2022, but remains a personal website of its founder Dr. Victor Chen. Nothing published on GoPeaks represents his formal affiliation.
Funded through a hybrid model of grants, gifts, and technology commercialization, GoPeaks started as a collection of research and technology development to accelerate and scale knowledge synthesis into real-world decision solutions. It is especially focused on knowledge graph-based prescriptive (causal) analytics. By grounding its solutions to improve multi-stakeholder performance management, its goal is to build a shared world brain serving broad interests of people and society. Please use the content on the GoPeaks website for non-commercial, educational purposes only.
Subscribe here for updates.
Join Knowledge Integration, Synthesis, and Engineering (KnISE) - a community of synthesizers, builders, and solvers for business and management.