Knowledge Graph Construction

Course in Winter 2024 at Institut Polytechnique de Paris
in the Master's program DataAI (CSC_5DA09_TP)
CC-BY 2024 Fabian M. Suchanek

Content

Language Models have revolutionized natural language processing. Yet, they can say wrong things in a very convincing way — they hallucinate. One solution to this problem can come from structured data such as knowledge graphs, which can serve to correct and inform the model. In this class, we will see how to bridge the gap between natural language (the sentence “Elvis is alive”) and structured information (the statement alive(Elvis)). We will cover the technical steps of information extraction: named entity recognition, entity disambiguation, and fact extraction. For each of them, we will see different methods: fine-tuning language models, prompt engineering, and training-free procedures. Finally, we will talk about techniques for knowledge cleaning: link prediction, entity alignment and rule mining.

Grading

The course is graded by 6 labs and a final exam. Discussing assignments together is allowed, but each student must write their own solution. No sharing of code, plagiarism entails a grade of 0 for the lab/exam.

Teachers:

Schedule

The class takes place at Telecom Paris.
Introduction (2024-11-15, room 1C47)
  1. Introduction to Information Extraction
  2. Knowledge Graphs
  3. Current research topics
Named Entity Recognition and Classification (2024-11-22, room 1D22)
  1. Knowledge Representation
  2. Named Entity Recognition and Classification
  3. A quick refresher of Regular Expressions
  4. Lab: training-free NERC
Typing and Disambiguation (2024-11-29, room 1A222)
  1. Prompt Engineering
  2. Entity Disambiguation
  3. Lab: Disambiguation with prompt engineering (without Fabian)
Fact extraction (2024-12-06, room 1A222)
  1. Fact Extraction
  2. Dependency Parsing
  3. Constrained Decoding
  4. Lab: Fact extraction by constrained decoding
Fact Extraction by Reasoning (2024-12-13, room 1A222)
  1. Extractive Entity Typing
  2. Information Extraction by Reasoning
  3. Lab: Max Sat
Rule Mining (2024-12-20, room 1A222)
  1. Rule Mining
  2. Link Prediction
  3. Lab: Rule mining
Semantic Web (2025-01-10, room 1A222)
  1. Semantic Web
  2. Reasoning on the Semantic Web (RDF, OWL, SHACL)
  3. Lab: KB cleanup
Exam (2025-01-17, room 0C04)
The exam is “closed-book”: no materials are allowed except for a pen.