wsheffel's starred repositories
knowledge-graph-from-GPT
Using GPT to organize and access information, and generate questions. Long term goal is to make an agent-like research assistant.
NeoGPT-Explorer
Knowledge-graph based chatbot using GPT3 and Neo4j
KnowledgeGraphGPT
Transform plain text into a visually stunning Knowledge Graph with GPT-4 (latest preview)! It converts text into RDF tuples, and highlights the most frequent connections with a vibrant color-coding system. Download the results as a convenient JSON file for easy integration into your own projects.
python-tutorial-notebooks
Python tutorials as Jupyter Notebooks for NLP, ML, AI
frame-semantic-transformer
Frame Semantic Parser based on T5 and FrameNet
knowledge-graph
Creates knowledge graph from information processed by "Entity Extraction and Linking" module, and "Emotion Recognition from Text" module
coling18tutorial
COLING 2018 Tutorial on Multilingual FrameNet: Automatic semantic role labeling for FrameNet
Knowledge-Graph-Embeddings-to-Implement-Explainability
Knowledge Graph Embeddings (KGE) to implement Explainable Artificial Intelligence. As AI develops users must know how algorithms make their decisions, especially for hazardous tasks such as driverless cars. Knowledge graphs are an inherently understandable form of text-based data created as an interconnected network of information. These can be converted into KGE by transforming the unqiue entites in the graph to vector representations. With these, predictions were made for missing/incorrect links in the network and further explainations were made by plotting the clusters of the data. Knowledge graphs and their embedded models were researched and four of these KGE were created and tested by their ability to rank the correct links from a Covid-19 dataset. This dataset was extracted from research papers about the virus to retrieve information quicker. The model which was most accurate was used to implement knowledge graph completion and explainability of the dataset using visual and textual interpretations. A 29,000-word thesis was written to describe the work done through the researching, testing and interpreting of this project.
framenet-tools
Annotate text with FrameNet frames and arguments.
KnowledgeGraphVerbalizer
These last years have witnessed the rise of knowledge graph technologies. Practically, semi-structured datasets (often available online through APIs and endpoints) allow data practitioners to build up complex use-cases interconnecting multiple data sources. However, technologies are often operating as black boxes and the need for explainability is increasing, in particular to keep track of the intermediate steps of the data pipelines. In this project, we would like the group to explore the possibility of verbalizing (creating a narrative) from knowledge graph excerpts. Technically, a browser interface able to query an open knowledge graph and render a text using for instance SimpleNLG <https://github.com/simplenlg/simplenlg> is envisioned.
Knowledge_Graphs-Text
Creating knowledge graphs from entities in large chunks of text
visual-essays
Tools for creating interactive essays from text, knowledge graphs, and other web content
knowledge-graph-with-spaCy
Creating a basic knowledge graph with spaCy and text data from the New York Times
Knowledge-graph-creation
This project is used to create knowledge graphs from the given input text and it would be used in analysing nlp parts
Triplet-extraction-from-text-and-creating-graph
Grammar Based triplet extraction from text & knowledge graph creation with visualization. Building a flask-based web application to create a knowledge graph with unstructured data.
visual-essays
Tools for creating interactive essays from text, knowledge graphs, and other web content
Knowledge_graph_from_Text_scraped_article
An application that scrape news article and creates a knowledge graph from it