School of Electronic Engineering and Computer Science

people menu

Dr Dimitrios Kartsaklis

Postdoctoral Research Assistant

Research Interests

  • Category-theoretic compositional models of natural language
  • Natural language semantics
  • Machine learning-Deep learning for NLP
  • Categorical Quantum Mechanics
  • Machine translation


I am a Greek computer scientist and computational linguist. I have completed my DPhil at the Quantum Group of the University of Oxford, where my research was focused on category-theoretic compositional models of natural language (thesis title: "Compositional Distributional Semantics with Compact Closed Categories and Frobenius Algebras"). I also hold an MSc in Artificial Intelligence from the University of Edinburgh. In the past I have worked as software engineer and system analyst for more than 15 years. At the same time I am an experienced technical translator/writer having many collaborations with the Greek academia and top publications such as Scientific American (Greek Edition). Other scientific interests include: distributional models of semantics; pregroup and categorial grammars; category theory; machine learning/deep learning (especially in relation to composition); machine translation and translation technologies; interactive MT and practical applications of MT; wide-coverage statistical parsing; quantum computing



For the recent years I mainly work with Mehrnoosh Sadrzadeh; I also collaborate with Bob Coecke and Stephen Pulman.



For datasets, code, word embeddings and other resources related to my work, please see the resource page of the CompLing Lab.


Selected publications

(For a full list please see my profile)

  • Syntax-Aware Multi-Sense Word Embeddings for Deep Compositional Models of Meaning. J. Cheng and D. Kartsaklis. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015 (pdfbibtex)
  • A Frobenius Model of Information Structure in Categorical Compositional Distributional Semantics. D. Kartsaklis, M. Sadrzadeh. 14th Meeting on the Mathematics of Language (MoL), 2015 (pdf, bibtex)
  • Open System Categorical Quantum Semantics in Natural Language Processing. R. Piedeleu, D. Kartsaklis, B. Coecke, M. Sadrzadeh. 6th Conference on Algebra and Coalgebra in Computer Science (CALCO), 2015  (pdf)
  • Evaluating Neural Word Representations in Tensor-Based Compositional Settings. D. Milajevs, D. Kartsaklis, M. Sadrzadeh, M. Purver. Proceedings of EMNLP 2014 (pdf, bibtex)
  • A Study of Entanglement in a Categorical Framework of Natural Language. D. Kartsaklis, M. Sadrzadeh. In Proceedings of the 11th Workshop of Quantum Physics and Logic (QPL 2014), EPTCS 172. 2014 (pdf, bibtex)
  • Resolving Lexical Ambiguity in Tensor Regression Models of Meaning. D. Kartsaklis, N. Kalchbrenner, M. Sadrzadeh. In Proceedings of the 52nd Annual Meeting of the Association of Computational Linguistics (ACL 2014). 2014 (pdf, bibtex)
  • Compositional Operators in Distributional Semantics. D. Kartsaklis. Springer Science Reviews, 2014 (pdf, bibtext)
  • Prior Disambiguation of Word Tensors for Constructing Sentence Vectors. D. Kartsaklis, M. Sadrzadeh. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP 2013), 2013. (pdf, bibtex
  • Reasoning about Meaning in Natural Language with Compact Closed Categories and Frobenius Algebras, D. Kartsaklis, M. Sadrzadeh, S. Pulman, B. Coecke. In Logic and Algebraic Structures in Quantum Computing and Information (pdf)
  • A Unified Sentence Space for Categorical Distributional-Compositional Semantics: Theory and Experiments, D. Kartsaklis, M. Sadrzadeh, S. Pulman. In Proceedings of COLING 2012, 2012 (pdfbibtex)

Return to top