Menu

School of Electronic Engineering and Computer Science

people menu

Dr Mehrnoosh Sadrzadeh

Senior Lecturer and EPSRC Career Acceleration Fellow

Research Interests

I am interested in the logical and mathematical structures governing artificial intelligence. In particular, I am interested in understanding how language works,  so we may enable computers to use it in ways similar to humans.

My current project is on combining statistical and logical models of language.  On the statistical side, I work with vector space models of real text. On the logical side, my work is based on categorial grammars such as CCG,  Lambek calculus, pregroup grammars.  I work with resources such as tensors and entangled states, which have proved invaluable for obtaining better experimental bounds. Similar models have been applied to reasoning about quantum protocols.

Previously,  I worked on algebraic and coalgebraic models of multi-agent information flow, where I developed a sound and complete algebraic semantics and a cut-free sequent calculus with adjoint modalities for a positive and an intuitionistic fragment of dynamic epistemic logic, with applications to reasoning about learning via communication and navigation. 


For an accessible  easy to read description of what I do and its connections to Quantum theory, see my QMUL Connect Bulletin entry



Collaborators
Abramsky, Balkir, Casadio, Clark, Coecke, Grefenstette, Hedges, Kartsaklisk, Milajevs, Muskens, Pulman, Purver, Preller, Roelleke (for the linguistics stuff) and Baltag, Coecke, Dyckhoff, Ma, Palmigiano, Panagaden, Pardo, Philips, Precup, Truffault (for the epistemic things).

Topics of Interest
Compositional Distributional Semantics
Category Theoretical Models of Natural Language
Pregroup Grammars, Vector Space Models
Dynamic Epistemic Logic, Algebra , Coalgebra, Proof Theory

Groups:
 
Joint leader of the natural language lab
Member of the theory group, 
Associate member of the cognitive science group. 

Fellow of the Higher Education  Academy (HEA), July 2016.

PC work:
European Summer School in Logic Language Information (ESSLLI) 2017, 
Federation of Logic Language Information (FoLLI)'s E.W.S. Beth Dissertation Prize Committee 2015 & 2016, 
International  Workshop on Logic Language Information and Computation (WoLLIC) 2016,2017.
International  Conference on Mathematical Foundations of Programming Semantics (MFPS) 2017,
International  Conference on Logical Aspects of Computational Linguistics (LACL) 2016, 
International  Conference on Formal Grammar 2016,  
International  Conference on Artificial Intelligence (IJCAI) 2016, 
International  Conference on Mathematics of Language (MoL) 2015, 2017,
International  Conference on Quantum Physics and Logic (QPL), 2011-16,  
International  Conference on Computability in Europe (CiE), 2014-16, 
International  Conference on Quantum Interactions (QI), 2011-15. 

Reviews for journals and other: TCS, MSCS, JoLLI, Entropy, JLC, CL, ACL, NAACL, EACL and EMNLP, ... . 

Organised Events:

Edited Volume

Projects
  • AFSOR project (with Oxford): Algorithmic and Logical Aspects when Computing Meanings.
  • Clothes Network Ltd: Compositional vector methods for request classification, with FayiMora Femi-Balogun.
  • EPSRC project:  New Foundational Structures for Engineering Verified multi-UAV's.
  • EPSRC Career Acceleration Fellowship: Foundational Structures for Compositional Meaning.
  • Done: EPSRC Postdoctoral Fellowship: (AlCoSeK) Alegbraic and Coalgebraic Semantics for Knowledge.
Media
Invited Talks

In specialised and/or Festschrift meetings:

Recent Papers  (for more please see  my google scholar page)
  1. Many Valued Generalised Quantifiers for Natural Language in the DisCoCat Model, Matej Dostal and Mehrnoosh Sadrzadeh, QMUL Technical Report.
  2. Distributional Inclusion Hypothesis for Tensor-based Composition, Dimitri Kartsaklis and Mehrnoosh Sadrzadeh,  6th International Conference on Computational Linguistics, Osaka, Japan, December 2016.
  3. A Compositional Distributional Inclusion Hypothesis, Dimitri Kartsaklis and Mehrnoosh Sadrzadeh,  the 9th edition of the Conference on Logical Aspects of Computational Linguistics, Nancy, France, December 2016.
  4. A Generalised Quantifier Theory of Natural Language in Categorical Compositional Distributional Semantics with Bialgebras, Jules Hedges and Mehrnoosh Sadrzadeh, 13th Int. Conference on Quantum Physics and Logic (QPL), Glasgow, June 2016, arXiv[1602.01635], submitted to MSCS.
  5. Quantifier Scope in Categorical Compositional Distributional Semantics, Mehrnoosh Sadrzadeh, Workshop on Semantic Spaces at the Intersection of NLP, Physics and Cognitive Science,Glasgow, June 2016, EPTCS proceedings.
  6. Context Update for Lambdas and Vectors, Mehrnoosh Sadrzadeh and Reinhard Muskens, NASSLLI workshop on Statistical and Logical Models of Meaning (SaLMoM), Rutgers, NJ, 2016.
  7. Lambdas and Vectors, Mehrnoosh Sadrzadeh and Reinhard Muskens, ESSLLI workshop on Distributional Semantics and Linguistics Theory (DSALT), Bolzano, 2016.
  8. Sentence Entailment in Compositional Distributional Semantics, Esma Balkir, Dimitri Kartsaklis and Mehrnoosh Sadrzadeh,  International Symposium on Artificial Intelligence and Mathematics (ISAIM), Florida, USA, January 2016, submitted to Annals of Maths and AI. 
  9. Distributional Sentence Entailment Using Density Matrices, Esma Balkir, Mehrnoosh Sadrzadeh, Bob Coecke, LNCS-FTP proceedings of TTCS, editors: MT Hajiaghayi MT, MR Mousavi,  volume, 9541, pages  1-22. 2015. 
  10. The Frobenius anatomy of word meanings II: possessive relative pronouns, Mehrnoosh Sadrzadeh, Stephen Clark, Bob Coecke, Journal of Logic and Computation, Essays dedicated to Roy Dyckhoff on the occasion of his retirement, S. Graham-Lengrand and D. Galmiche (eds.), Volume 26, pages 785-815,  2016.
  11. IR meets NLP: On the Semantic Similarity between Subject-Verb-Object Phrases, Dmitrijs Milajevs, Mehrnoosh Sadrzadeh, Thomas Roelleke, ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR), USA, 2015. 
  12. The Use of English Colour Terms in Big Data, Dimitris Mylonas, Matthew Purver, Mehrnoosh Sadrzadeh, Lindsay MacDonald and Lewis Griffin,  in Proceedings of the 2015 Meeting of the International Colour Association (AIC), Tokyo, May 2015.
  13. A Frobenius Model of Information Structure in Categorical Compositional Distributional Semantics. Dimitri Kartsaklis, Mehrnoosh Sadrzadeh. 14th Meeting on the Mathematics of Language (MoL), 2015.
  14. Open System Categorical Quantum Semantics in Natural Language Processing. Robin Piedeleu, Dimitri Kartsaklis, Bob Coecke, Mehrnoosh Sadrzadeh, Conference on Algebra and Coalgebra in Computer Science (CALCO), 2015.
  15. Evaluating Neural Word Representations in Tensor-Based Compositional Settings, Dmitrijs Milajevs, Dimitri Kartsaklis, Mehrnoosh Sadrzadeh, Matthew Purver, 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Qatar, October 2014.
  16. Resolving Lexical Ambiguity in Tensor Regression Models of Meaning, Dimitri Kartsaklis, Nal Kalchbrenner and Mehrnoosh Sadrzadeh, In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL): Short Papers. Baltimore‚ USA, June, 2014. 
  17. Concrete Models and Empirical Evaluations for the Categorical Compositional Distributional Model of Meaning, Ed Grefenstette, Mehrnoosh Sadrzadeh, Journal of Computational Linguistics, Volume 41, Pages 71-118, March 2015.
  18. A Low-Level Treatment of Generalized Quantifiers in Categorical Compositional Distributional Semantics, Ondrej Rypacek and Mehrnoosh Sadrzadeh, Second Workshop on Natural Language and Computer Science, A workshop affiliated with the joint meeting of Computer Science Logic (CSL) and Logic in Computer Science (LiCS), Vienna, July 2014. 
  19. Word Order Alternations in Sanskrit via Precyclicity in Pregroup Grammars, Claudia Casadio and Mehrnoosh Sadrzadeh, In Horizons of the Mind, Essays dedicated to Prakash Panangaden on the occasion of his 60th birthday, LNCS 8464, May 2014. 
  20. A Study of Entanglement in a Categorical Model of Natural Language, Dimitri Kartsaklis and Mehrnoosh Sadrzadeh,  11th workshop on Quantum Logic and Physics (QPL), Kyoto University, June 2014. arXiv:1405.2874.
  21. Semantic Unification: a sheaf theoretic approach to natural language, Samson Abramsky and Mehrnoosh Sadrzadeh, In: Catgories and Types in Logic, Language, and Physics, Essays dedicated to Jim Lambek on the occasion of his 90th birthday, Casadio et al (eds.), LNCS 8222, pages 1- 13, 2014. arXiv:1403.3351
  22. Algebraic Semantics and Model Completeness for Intuitionistic Public Announcement Logic, Minghui Ma, Alessandra Palmigiano and Mehrnoosh Sadrzadeh, Annals of Pure and Applied Logic, Volume 165, Pages 963--995, 2014.
Ph.D. Students
  • Gijs Wijnholds (QMUL, with Robinson)
  • Dmitrijs Milajevs (QMUL, with Dr Purver)
  • Dimitri Kartsaklis (graduated, Oxford, with Profs Coecke and Pulman)
  • Edward Grefenstette (graduated, Oxford,  with Profs Coecke and Pulman)
  • Pere Pardo (graduated, Barcelona, with Prof Godo)
Teaching

Alternative Choir and Music Society, Oct 2009 to 2012. Wolfson College, Oxford.

Return to top