There exists a significant disconnect between linguistic research and pedagogical practice in the Persian classroom. Discover what this means for Persian and multilingual, low-resource NLP.

Narratives are foundational to human expression across cultures. Discover what this means for Persian and multilingual, low‑resource NLP.

TaarofBench is the first benchmark for Persian taarof, a complex politeness system missing from existing cultural AI tests. Across 450 scenarios, LLMs underperform humans by 40–48% and often misinterpret politeness. Fine-tuning improves cultural alignment, highlighting the need for culturally aware AI.

Responsible AI is an umbrella term used to describe an approach that considers the business, legal, and ethical choices in the design, development, deployment, and adoption of AI. Learn how this advances responsible, transparent, and inclusive AI practice.

This paper proposes a new computational architecture for narrative-driven case elicitation, describes six new legal narrative corpora, and evaluates two different approaches to creating legal narrative schemas, the first using language models, and the second using event sequence alignment. See how the authors model structure, events, and time in real‑world texts.

This paper provides an in-depth description of the Advanced Narrative Analytics System Infrastructure (ANAnSI), which performs content extraction and detailed narrative analytics for knowledge discovery within a distributed high-performance system infrastructure. See how the authors model structure, events, and time in real‑world texts.

The authors describe the application of advanced Natural Language Processing (NLP) and Artificial Intelligence (AI) methods to automatically discover and analyze important information from text. See how the authors model structure, events, and time in real‑world texts.

Over the past several decades, the S&T landscape has transformed into a more geographically distributed, more interconnected, and more dynamic arena for collaboration and knowledge exchange. Read for methods, evaluations, and why the findings matter for scalable AI systems.

TimeML is an annotation scheme for capturing temporal information in text. See how the authors model structure, events, and time in real‑world texts.

The effectiveness of sex offender management policies and supervision approaches relies on the ability of criminal justice professionals to accurately differentiate sexual offenders according to their risk to recidivate. Read for methods, evaluations, and why the findings matter for scalable AI systems.

This chapter provides a review of the research previously conducted on Persian heritage linguistics, with a focus on the domains of phonology, morphology and syntax. Discover what this means for Persian and multilingual, low‑resource NLP.

The U. See how the authors model structure, events, and time in real‑world texts.