• Home
• Publications
• Talks
• CV
• Software

Greetings!

I am Kokos [he/him]. I enjoy (occasionally) thinking, reading, and talking about stuff at the intersection of mathematical logic, linguistics, and machine learning. This website tracks and presents (some of) my work.

Whereabouts / Short CV

Over the last few years, I have been alternating between academic and private research. I'm currently working as an internal advisor for Input Output (IOHK). I might say more about what I'm doing when I figure it out myself. :)

On the academic front, I earned my PhD in Computational Linguistics from Utrecht University. Following my doctorate, I did a post-doc at Aalto University. Prior to my doctorate, I obtained a master's degree in AI (also from Utrecht), and an ECE diploma from the Aristotle University of Thessaloniki.

A longer version of the above can be found at my CV.

Research

My published research revolves around structured representation learning, neurosymbolic reasoning, and type-driven approaches to syntactic parsing and semantic compositionality. I am especially interested in the interface between formal and data-driven methods; if that floats your boat rubber duck, you can have a look at my publications page.

My latest output is "Nominal Class Assignment in Swahili: A Computational Account" (CliC-it-2024, October 2024).

Thesis

My dissertation is titled "Dependency as Modality, Parsing as Permutation: A Neurosymbolic Perspective on Categorial Grammars". It advocates for the use of modalities as dependency annotations in type-logical grammars, and explores the parsing-as-deduction paradigm from a contemporary neurosymbolic perspective.

People thought it was good: it is one of the two recipients of the 2024 E. W. Beth Dissertation Prize. You can find a faithful copy of the physical print here. If (for whatever reason) you're interested in an actual physical copy, feel free to send me a message.

Recent & Upcoming Talks

Here's a list of my recent and upcoming talks (more here):

• Grammaticality as Provability
  May 28, 2025 in Groningen
  Invited @ Logic seminar of the University of Groningen
• On Tables with Numbers, with Numbers
  May 4, 2025 in Virtual
  Contributed @ The NAACL 2025 Workshop on Language Models for Underserved Communities
• LLM-free Representation Learning from Theorem Structure
  April 21, 2025 in Gothenburg
  Invited @ Deep-Learning Models for Mathematics and Type Theory
• Structure-Aware Neural Representations of Agda Programs
  April 7, 2025 in Edinburgh
  Contributed @ EuroProofNet-WG5: Theorem Proving and Machine Learning in the age of LLMs
• Learning Structure-Aware Representations of Dependent Types
  December 11, 2024 in Vancouver
  Contributed (Poster) @ The Thirty-Eighth Annual Conference on Neural Information Processing Systems
• Algebraic Positional Encodigns
  December 11, 2024 in Vancouver
  Contributed (Poster, Spotlight) @ The Thirty-Eighth Annual Conference on Neural Information Processing Systems

Teaching

I haven't taught in a while. Aeons ago, I participated in various capacities in the following courses:

• Compositional Models of Vector-Based Semantics (ESSLLI 2022)
• Logic & Language (2020-2021, main lecturer)
• Logic & Language (2018-2019, 2019-2020, 2021-2022, lectures & project supervision)
• Machine Learning for Human Vision & Language (2019-2020, tutorials)
• Advanced Topics in Cognitive Modelling (2018-2019, tutorials)