Zhijin Guo

Zhijin Guo

Postdoctoral Researcher at University of Oxford

Posts by Collection

portfolio

publications

Extract: Explainable transparent control of bias in embeddings

Published in AEQUITAS 2023: AEQUITAS 2023 First AEQUITAS Workshop on Fairness and Bias in AI co-located with ECAI 2023, 2023

A suite of methods for controlling bias in knowledge graph embeddings while maintaining model utility and transparency.

Recommended citation: Z. Guo, Z. Xu, M. Lewis, and N. Cristianini, "Extract: Explainable transparent control of bias in embeddings," in AEQUITAS 2023: AEQUITAS 2023 First AEQUITAS Workshop on Fairness and Bias in AI co-located with ECAI 2023, 2023.

On compositionality in data embedding

Published in International Symposium on Intelligent Data Analysis, Springer, 2023

An analysis of compositionality principles in various data embedding approaches and their applications.

Recommended citation: Z. Xu, Z. Guo, and N. Cristianini, "On compositionality in data embedding," in International Symposium on Intelligent Data Analysis, Springer, 2023, pp. 484–496. https://doi.org/10.1007/978-3-031-30047-9_38

Published in , 1900

Bridging social structure and discourse

Published in Preparing to submit to the ACL Rolling Review (ARR), 2025

A study on bridging social network structures and discourse patterns using advanced NLP and graph neural network techniques.

Recommended citation: Z. Guo, Z. Li, B. Tyler, X. Dong, and J. Pierrehumbert, "Bridging social structure and discourse," Preparing to submit to the ACL Rolling Review (ARR), 2025.

Quantifying compositionality in classic and state-of-the-art embeddings

Published in Under review by the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

A comprehensive evaluation of compositionality in embeddings across SBERT, GPT, LLAMA, and Knowledge Graph embeddings.

Recommended citation: Z. Guo, C. Xue, Z. Xu, et al., "Quantifying compositionality in classic and state-of-the-art embeddings," Under review by the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025.

talks

teaching