This device is not compatible.
You will learn to:
Preprocess the text by finding patterns.
Use spaCy to resolve coreferences.
Perform named entity recognition.
Create and visualize a knowledge graph using the NetworkX library.
Skills
Natural Language Processing
Text Preprocessing
Knowledge Graphs
Prerequisites
Basic understanding of text preprocessing
Familiarity with NLP concepts
Understanding of named entity recognition
Familiarity with graphs
Technologies
spaCy
Python
NetworkX
Matplotlib
Project Description
A knowledge graph is widely used to concentrate knowledge in a compact and cohesive form for easy retrieval. Creating a knowledge graph involves getting data, preprocessing it, converting words to their root forms, and extracting subject-predicate-object triple.
In this project, we’ll use The Wikipedia Library to get English language sentences and pass them through every step listed above to create a knowledge graph at the end. The graph will also facilitate information extraction via simple queries. All the text processing will be done via the open-source NLP library, spaCy. The network creation and information extraction will be completed using the NetworkX library, and lastly, the pyvis library will be used to display the knowledge graph.
Project Tasks
1
Getting Started
Task 0: Get Started
Task 1: Import Libraries
2
Data Preparation
Task 2: Load the Data
Task 3: Preprocess the Data
3
Application of NLP Techniques
Task 4: Recognize Named Entities
Task 5: Compute Coreference Clusters
Task 6: Resolve Coreferences
Task 7: Extract Relationships
4
The Knowledge Graph
Task 8: Create a Graph
Task 9: List the Related Entities
Congratulations!