This repository contains code and models for the paper: Semantic Graphs for Generating Deep Questions (ACL 2020).

This AI-powered tool extracts Subject-Predicate-Object (SPO) triplets from unstructured text using LLMs, performs entity standardization and relationship inference, and generates interactive, community-detected knowledge graphs with rich visualizations.

Rematch: Robust and Efficient Matching of Local Knowledge Graphs for Improved Structural and Semantic Similarity

XSLT processors that automatically generate instances of LinkedMDR ontology

An attempt to establish the computational basis of humor.

quick and dirty code for finding isomorphic (edge structure based) directed semantic graphs

A novel method for the construction and weighing of the semantic graph, which contains text segments (terms or sentences) as nodes and weighted edges that capture the semantic relatedness (i.e. relatedness in meaning) between nodes and experimental evaluation of semantic rank in keyword extraction and text summarization tasks.

The Dynamic Knowledge System (DKS) develops adaptive knowledge representation models that evolve in real-time, learning, updating, and reasoning under uncertainty.

examples of directed semantic graphs and simple Knowledge Bases for experiments

NLP toolkit for preprocessing, embedding, topic modeling, and graph construction. Built for integration with NP-Backend-Dockers.

Image recognition system by semantic graph correction

customised version of conceptnet 5 (and utils) used as a source of input spaces, analogies/mappings and frames in Conceptual Blending experiments

Unified Parallel Semantic Log Parsing based on Causal Graph Construction for Attack Attribution

converts directed semantic graphs between four file formats: csv, tgf, pro, dt