Knowledge Graph Embeddings for NLP: From Theory to Practice

KGE4NLP Tutorial website, COLING 2022 Conference

Theory Session:

Hands-On Session:

Welcome to the world of Knowledge Graphs Embeddings for NLP tutorial, save the date of 16th of October from 16:00 - 20:00 KST, 202, HICO Gyeongju, Republic of Korea, during COLING 2022 - The 29th International Conference on Computational Linguistics, Conference dates: October 12th-17th 2022.


Knowledge graph embeddings are supervised learning models that learn vector representations of nodes and edges of labeled, directed multi-graphs. We describe their design rationale, and explain why they are receiving growing attention within the graph representation learning and the broader NLP communities. We highlight their limitations, open research directions, and real-world use cases. Besides a theoretical overview, we also provide a handson session, where we show how to use such models in practice.


Luca Costabello is research scientist in Accenture Labs Dublin. His research interests span knowledge graph applications, machine learning for graphs, and explainable AI. He is the creator of AmpliGraph, a Python library for knowledge graph embedding models (1.6k github stars). He organised and co-presented the first edition of the KGE tutorial, co-located with ECAI-20. He led the organization of the first edition of the Explainable AI tutorial at AAAI-199, an event with over 200 attendees. Before joining Accenture, Luca was research scientist at Fujitsu Ireland, PhD student at Inria France, and research engineer at Telecom Italia. Luca co-authored works published in AI and NLP conferences (including ACL and EMNLP) and regularly serves as PC member for flagship conferences. Up-to-date publication list available at Contact:

Adrianna Janik is a research engineer at Accenture Labs Dublin. Her research interests are interpretability in machine learning, deep learning, and recently knowledge graphs. She co-organised and presented the first edition of the KGE tutorial at ECAI-20. She has double Masters in Data Science with a minor in entrepreneurship from the European Institute of Innovation and Technology (EIT), at the University of Nice - Sophia Antipolis and at the Royal Institute of Technology, Stockholm. During studies, she did her thesis internship at the Montreal Institute for Learning Algorithms. She also has a Bachelors in Control Engineering and Robotics from the Wroclaw University of Technology and used to work as a software engineer at Nokia. Contact:

Eda Bayram recently defended her doctoral thesis titled “Representation Learning for Multirelational Data” at the Swiss Federal Institute of Technology (EPFL). She received her master’s degree and diploma from Middle East Technical University (METU), majoring in signal processing. She is primarily interested in machine learning for graph-structured data. Contact:,

Sumit Pai is a research engineer at Accenture Labs Dublin. His research interests include knowledge graphs, representational learning, computer vision and its applications. He co-organised and presented the first edition of the KGE tutorial at ECAI-20. Sumit has also worked as an engineer (Computer Vision) at Robert Bosch, India. He has done his Masters in Neural Information Processing from University of Tübingen, Germany. Contact

Cite as

  author       = {Adrianna Janik and
                  Eda Bayram and
                  Luca Costabello and
                  Sumit Pai},
  title        = ,
  month        = jan,
  year         = 2023,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.7535740},
  url          = {}

Not enough? Why not check out 1st edition of the tutorial held during ECAI 2020?