Bias in Automatic Knowledge Graph Construction

Edgar Meij, Tara Safavi, Chenyan Xiong, Miriam Redi, Gianluca Demartini, Fatma Özcan

Please visit for more details on the workshop schedule.


Welcome and Opening Remarks
Keynote: Jahna Otterbacher, Open University of Cyprus. Bias in Data and Algorithmic Systems: A "Fish-Eye View" of Problems, Solutions and Stakeholders.
Invited paper Joseph Fisher, Dave Palfrey, Arpit Mittal and Christos Christodoulopoulos. Measuring social bias in knowledge graph embeddings.
Christine Wolf. From Knowledge Graphs to Knowledge Practices: On the Need for Transparency and Explainability in Enterprise Knowledge Graph Applications.
Shubhanshu Mishra, Sijun He and Luca Belli. Assessing Demographic Bias in Named Entity Recognition.
Emma Gerritse, Faegheh Hasibi and Arjen P. de Vries. Bias in Conversational Search: The Double-Edged Sword of the Personalized Knowledge Graph.
Keynote: Jieyu Zhao. Detecting and mitigating gender bias in NLP.
Plenary Discussion, Wrap-up and Concluding Remarks


Knowledge Graphs (KGs) store human knowledge about the world in structured format, e.g., triples of facts or graphs of entities and relations, to be processed by AI systems. In the past decade, extensive research efforts have gone into constructing and utilizing knowledge graphs for tasks in natural language processing, information retrieval, recommender systems, and more. Once constructed, knowledge graphs are often considered as “gold standard” data sources that safeguard the correctness of other systems. Because the biases inherent to KGs may become magnified and spread through such systems, it is crucial that we acknowledge and address various types of bias in knowledge graph construction.

Such biases may originate in the very design of the KG, in the source data from which it is created (semi-)automatically, and in the algorithms used to sample, aggregate, and process that data. Causes of bias include systematic errors due to selecting non-random items (selection bias), misremembering certain events (recall bias), and interpreting facts in a way that affirms individuals’ preconceptions (confirmation bias). Biases typically appear subliminally in expressions, utterances, and text in general and can carry over into downstream representations such as embeddings and knowledge graphs.

This workshop – to be held for the first time at AKBC 2020 – addresses the questions: “how do such biases originate?”, “How do we identify them?”, and “What is the appropriate way to handle them, if at all?”. This topic is as-yet unexplored and the goal of our workshop is to start a meaningful, long-lasting dialogue spanning researchers across a wide variety of backgrounds and communities.