Simon Clematide

Simon Clematide is a Professor in the Department of Computational Linguistics within the Faculty of Arts and Social Sciences at the University of Zurich. With a publication record spanning over two decades from 2001 to 2025, he has established himself as a leading researcher in computational linguistics, particularly focusing on multilingual natural language processing, historical document analysis, and OCR applications.

His research interests encompass Natural Language Processing, Computational Linguistics, Multilingual Embeddings, Historical Document Analysis, OCR Processing, and Text Normalization. Clematide's work demonstrates a strong emphasis on practical applications of NLP in digital humanities, with significant contributions to processing historical texts and multilingual resources. His recent work has increasingly incorporated large language models and transformer architectures for tasks ranging from text embedding evaluation to historical document processing.

Clematide's publication trends show a consistent focus on multilingual NLP with particular expertise in Germanic languages and historical text processing. His work bridges theoretical linguistics with practical computational approaches, often addressing challenges in low-resource language scenarios and historical document digitization. Recent publications demonstrate increasing integration of LLMs into traditional NLP pipelines for tasks like paraphrase detection, job advertisement analysis, and historical text normalization.

His collaborative work includes significant contributions to shared tasks and benchmarks in the NLP community, particularly through the HIPE (Historical Information Processing Evaluation) shared tasks. These efforts have helped establish standardized evaluation frameworks for named entity recognition in historical documents.

Clematide has been actively involved in several major research projects related to historical newspaper content mining, including the impresso project which focused on cross-lingual historical document processing. His work often involves interdisciplinary collaboration between computer scientists, linguists, and historians.