Research Overview
My research bridges two worlds: the deep, formal study of language structure and the applied challenges of multilingual AI systems. On one side, I investigate the architecture of grammar — the primitive relations that underlie complex predicates, morphology, and meaning. On the other, I develop computational approaches for social media analysis, narrative and event extraction, scientometrics, and AI-assisted language learning, with particular attention to Persian and other low-resource languages. Across these efforts runs a single goal: to understand how language works at its core and to design AI systems that respect its structural complexity, cultural richness, and human purpose.
This broader research direction is deeply influenced by the work of Jean-Roger Vergnaud, whose view of grammar as a system built from abstract primitives, graph-like relations, and event structure continues to shape my thinking. His ideas raise a fundamental question that guides my work: what is the underlying architecture of language, and how might it inform the future of linguistically grounded AI?
The research programs below reflect the main directions through which I pursue these questions.
Research Programs
The Architecture of Language
This research program investigates the structural foundations of human language, focusing on the syntax–semantics interface and the mechanisms that link grammatical structure to meaning. My work examines complex predicates, event structure, and morphological composition across languages (particularly in Persian and Armenian) with the goal of developing formal and computational models of how language encodes meaning.
Application areas
-
Computational modeling of grammar
-
Cross-linguistic analysis of complex predicates
-
Persian and Armenian linguistic resources
-
Linguistically informed NLP architectures
Linguistically Grounded AI
This program explores how insights from linguistic theory can inform the design and evaluation of AI systems that process language. While modern language models rely heavily on large-scale statistical learning, this research investigates how linguistic structure, semantic interpretation, and cross-linguistic variation can improve multilingual and low-resource language technologies.
Application areas
-
Multilingual natural language processing
-
Low-resource language technologies
-
Linguistic evaluation of large language models
-
AI-assisted language learning systems
Language in Social Systems
Language plays a central role in shaping narratives, ideologies, and collective behavior. This research program applies computational linguistics and narrative analysis to understand how language operates within complex social and political systems, particularly in digital environments where discourse spreads rapidly and influences public perception.
Application areas
-
Social media discourse analysis
-
Narrative analytics and ideology detection
-
Online community and network analysis
-
Computational analysis of political and cultural narratives
The Science of Knowledge
Scientific knowledge evolves through networks of researchers, publications, and ideas. This research program uses natural language processing, scientometrics, and network analysis to study how knowledge develops, spreads, and transforms across disciplines. By analyzing large bodies of scholarly literature, the goal is to better understand the dynamics of discovery and the structure of scientific fields.
Application areas
-
Bibliometric and citation network analysis
-
Mapping research landscapes and emerging fields
-
Knowledge graph construction for scientific literature
-
Tools for research discovery and knowledge synthesis
