Student, Wolfson College
Room 217, Wolfson Building, Parks Road, Oxford OX1 3QD
I am a Greek computer scientist, currently finishing up a DPhil in Computer Science at the University of Oxford. My research is focused on Computational Linguistics, and specifically on Compositional-Distributional models of meaning. Before I came to Oxford I've been working for many years as a software engineer and a translator/editor of CS textbooks and scientific journals. I have an MSc in Artificial Intelligence from the University of Edinburgh.
While in Oxford I mainly work with Mehrnoosh Sadrzadeh; I also collaborate with Stephen Pulman, Bob Coecke, Edward Grefenstette, and Nal Kalchbrenner. In the past I worked with Mark Steedman and Panagiotis Kanavos.
- Computational Linguistics tutor (Hilary 2012- 13, Hilary 2013-14)
- Object Oriented Programming tutor (Michaelmas 2013-14)
- Concurrent Programming tutor-Keble College (Hilary 2013-14)
Two MSc projects:
- Jianpeng Cheng, "Investigating the Role of Prior Disambiguation in Deep Learning Compositional Models of Meaning", 2014
- Jiannan Zhang, "A Generic Evaluation for a Categorical Compositional-Distributional Model of Meaning", 2014
- 5-12-2013, Queen Mary University of London: Disambiguation in Compositional Distributional Models of Meaning
- COLING 2012 term-definition dataset
- CoNLL 2013 verb disambiguation dataset
- EMNLP 2013 transitive version of the Mitchell and Lapata (2010) verb-object dataset -- original human judgements
- QPL 2014 transitive version of the Mitchell and Lapata (2010) verb-object dataset -- new human judgements
- A news article about our QPL 2014 paper on entanglement in corpus linguistics (co-authored with M. Sadrzadeh) from technology.org.
- Another one for one of our older papers (co-authored with Sadrzadeh, Pulman and Coecke) regarding the use of Frobenius Algebras in language.
Investigating the Role or Prior Disambiguation in Deep−Learning Compositional Models of Meaning
Jianpeng Cheng‚ Dimitri Kartsaklis and Edward Grefenstette
In Learning Semantics workshop‚ NIPS 2014. Montreal‚ Canada. December, 2014.
Evaluating Neural Word Representations in Tensor−Based Compositional Settings
Dmitrijs Milajevs‚ Dimitri Kartsaklis‚ Mehrnoosh Sadrzadeh and Matthew Purver
In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha‚ Qatar. October, 2014. Association for Computational Linguistics.
A Study of Entanglement in a Categorical Framework of Natural Language
Dimitri Kartsaklis and Mehrnoosh Sadrzadeh
In Proceedings of the 11th Workshop on Quantum Physics and Logic (QPL). Kyoto‚ Japan. June, 2014.