Spelling Normalization Professors and Supervisors

Joakim Nivreمشاهده پروفایل

استاد

Helmholtz Centre for Environmental ResearchGermany

Joakim Nivre is a Professor at Uppsala University's Department of Linguistics and Philology. He is a leading researcher in computational linguistics, with a focus on dependency parsing, Universal Dependencies (UD) framework development, and multilingual NLP applications. His recent work explores LLMs in climate change discourse analysis, pharmacovigilance explainability, and historical text processing. Key research areas: Dependency parsing theory, Universal Dependencies standardization, LLM evaluation Collaborations: SweSAT-1.0 benchmark development, ClimateEval project, PARSEME integration His 2025-2023 publications demonstrate expertise in explainable AI for healthcare, synthetic data generation for idioms, and multilingual benchmark design. Notably, he co-developed SweSAT-1.0 to evaluate Swedish LLMs and contributed to typology-informed UD revisions. Despite extensive work in NLP, no scientific awards are mentioned in available texts.

پروفایل رسمی دانشگاه

Dilara Torunoğlu Selametمشاهده پروفایل

مدرس

Istanbul Technical UniversityTurkey

Dilara Torunoğlu Selamet serves as a Lecturer in the Department of Computer Engineering within the Faculty of Computer and Informatics at Istanbul Technical University. Holding a PhD, she specializes in Natural Language Processing for Turkish, with research emphases on social media text normalization, named entity recognition, and sentiment analysis. Her academic credentials feature: PhD in Computer Engineering, Istanbul Technical University (awarded circa 2013) Master of Science in Computer and Information Sciences (Non-thesis), Doğuş University (2009-2013) Bachelor of Science in Computer Engineering, Doğuş University (2004-2009) Dilara's scholarship tackles the complexities of Turkish NLP, a language with rich morphology. She has made notable contributions to text normalization for social media platforms, named entity recognition in authentic datasets, and semantic smoothing techniques for sentiment classification. Her work often bridges theoretical NLP with practical applications, as seen in resource-building projects like the ITU Web Treebank and Turkish sign language corpora. Her publication record (2011-2021) demonstrates methodical growth: initial work on text classification (2011) evolved into named entity recognition (2013) and social media normalization (2014, 2017), then expanded to data augmentation (2020-2021) and sign language processing (2020). This trajectory reflects her commitment to advancing Turkish NLP through both foundational research and innovative resource development. While no specific awards are documented, her research impact is evidenced by an h-index of 4 and over 127 citations in Scopus. Available information does not indicate any students supervised or research grants obtained. She is affiliated with Istanbul Technical University's Department of Computer Engineering, but no laboratory or research team memberships are specified in public profiles.

پروفایل رسمی دانشگاه

Jocelyn R. Folkمشاهده پروفایل

دانشیار

Kent State UniversityUnited States

Reading
Spelling
Dyslexia
+۳ مورد دیگر

Jocelyn R. Folk is an Associate Professor & Associate Chair at Kent State University's Department of Psychological Sciences. Her research focuses on cognitive processes in written language comprehension and production, particularly examining reading and spelling abilities across diverse populations. Education: Ph.D., University of South Carolina (1997) Using eye-tracking technology, Dr. Folk investigates how individuals learn new word meanings and spellings through text, analyzing moment-to-moment cognitive processing. Her work also examines acquired language impairments to understand normal language processing mechanisms. Publications demonstrate expertise in psycholinguistics, cognitive neuropsychology, and educational assessment. Key research trends include: eye movement patterns during reading, individual differences in lexical acquisition, orthographic-semantic interactions, and technological applications in cognitive research. Her laboratory facilities include state-of-the-art eye tracking equipment for empirical studies.

پروفایل رسمی دانشگاه

Claudia Stockمشاهده پروفایل

مدرس ارشد

Julius-Maximilians-Universität WürzburgGermany

Claudia Stock, Ph.D., is a Senior Academic Councillor (AOR) at the Chair of Pedagogy and Intervention for Language and Communication Impairments within the Institute for Special Education at the University of Würzburg's Faculty of Human Sciences. She holds a Diplom in Psychology (2001) and a doctoral degree (2005) from the same institution. Her academic career spans over two decades, with continuous service at the University of Würzburg since 2001. Dr. Stock's research focuses on dyslexia, phonological awareness, curriculum-based measurement (CBM), and the history of psychology and speech therapy. Her work demonstrates a consistent emphasis on developing and validating assessment tools for reading and writing disorders, particularly through projects like the German Spelling Tests (DERET) and Basic Competencies for Reading and Spelling Performance (BAKO). She has made significant contributions to understanding the relationship between phonological awareness and reading development in primary school children. Her publication record shows a clear trajectory from foundational research on phonological awareness and dyslexia toward practical applications in educational settings. Recent work emphasizes curriculum-based measurement in schools with a focus on language support and the re-normalization of spelling tests for elementary school children. Her scholarship bridges historical perspectives with contemporary assessment and intervention approaches. Research Prize of the Federal Association for Dyslexia and Dyscalculia (2005) Prize for scientific publication by the German Society for Psychology (2004) Dr. Stock plays a vital role in teacher education, particularly in speech therapy training and the Master's program in special education. She serves as contact person for special education internships and participates in state examination committees. Her professional memberships include the Federal and State Association for Dyslexia and Dyscalculia Bavaria (BVL and LVL) and the German Morbus Chron/Colitis ulcerosa Association (DCCV).

پروفایل رسمی دانشگاه

Marcel Bollmannمشاهده پروفایل

دانشیار

Linköping UniversitySweden

Marcel Bollmann is an Associate Professor at the Department of Computer and Information Science (IDA) at Linköping University, Sweden, where he leads research in the Artificial Intelligence and Integrated Computer Systems (AIICS) division. His work focuses on natural language processing (NLP), machine learning, and computational linguistics, particularly in under-resourced languages, multilinguality, and historical document analysis. Education: He holds a PhD in Computational Linguistics from Ruhr-Universität Bochum (2018), funded by projects on historical German language corpora. Previously, he was a postdoc at the University of Copenhagen (2018–2021), supported by an EU Marie Skłodowska-Curie Fellowship, and an assistant professor at Jönköping University (2021–2023), where he developed AI Engineering courses. Research: Bollmann’s interests include linguistically-informed NLP approaches, historical text normalization, and improving NLP accessibility across language genres. His work has addressed challenges like morphology-aware models and low-resource language support. Awards: His 2021 paper on morphology’s role in error analysis won the EACL Best Long Paper Award. He also contributed to the ACL Anthology as Site Development Lead, advancing NLP infrastructure. Advising & Grants: He has supervised projects on historical language corpora and received funding from EU initiatives. His lab collaborations focus on advancing AI through interdisciplinary methods. Labs/Teams: Active in the AIICS division at IDA, contributing to WASP (Wallenberg Autonomous Systems Program) and other interdisciplinary AI initiatives.

پروفایل رسمی دانشگاه

Pierrette Bouillonمشاهده پروفایل

پژوهشگر

University of GenevaSwitzerland

Pierrette Bouillon is affiliated with the University of Geneva as a researcher, focusing on machine translation, accessible communication, and language technology applications in healthcare. Her work bridges computational linguistics, speech processing, and inclusive design. Institution: University of Geneva Research Focus: Medical translation, sign language processing, text/pictograph translation Research Interests : Bouillon specializes in machine translation and computational linguistics , with particular emphasis on: Accessible communication for patients with language barriers Sign language and pictograph translation systems (e.g., BabelDr) Speech-to-speech translation in emergency settings Text simplification for intellectual disabilities Historical French normalization for NLP Multilingual speech recognition and post-editing Article Trends : Her recent publications highlight the integration of large language models with accessibility tools in healthcare, focusing on Swiss French sign language corpora , pictograph sequences , and spontaneous speech simplification . Work spans both NLP and human-computer interaction in medical contexts. Education and Teaching : While specific educational details are omitted, Bouillon contributes to translation pedagogy through tools like COPECO and MT3 , integrating speech technologies into post-editing workflows.

پروفایل رسمی دانشگاه

Michael McCloskeyمشاهده پروفایل

استاد

Johns Hopkins UniversityUnited States

Michael McCloskey is a Professor at the Johns Hopkins University within the Krieger School of Arts and Sciences , where he serves as the Homewood IRB Chair. His research spans reading and writing , visual perception , cognitive neuropsychology , and foundations of cognitive science . As director of the Cognitive Neuroscience Lab , he investigates normal and impaired cognitive functions through behavioral and neuroimaging techniques. Education : PhD in Cognitive Science from Princeton University His research focuses on understanding mental representations and processes in reading, spelling, and writing , analyzing deficits in brain-damaged and neurotypical individuals. Projects include exploring object orientation and shape representation using fMRI and behavioral studies, and addressing foundational issues in cognitive science, such as representational/computational models of the mind. Recent work examines the relationship between graphomotor plans and visual word recognition, and the role of object-part axes in tactile vs. visual perception. His lab's methodologies include cognitive neuropsychological studies of adults and children, computational modeling, fMRI, and ERP. Collaborative efforts with Dr. Brenda Rapp resulted in the edited volume Developmental Dysgraphia (2017). Former students like Pang Chaisilprungraung (postdoc at Walter Reed) and Gali Ellenblum (Apple MLE) highlight his mentorship success. Key scientific contributions include: (1) both-edges representations for letter position in reading/spelling, (2) compositional orientation representations in object perception, (3) graphomotor buffer in writing processes, and (4) the dissociation between MVPA and repetition suppression in neural orientation coding.

پروفایل رسمی دانشگاه

Eva Petterssonمشاهده پروفایل

پژوهشگر

Uppsala UniversitySweden

Eva Pettersson is a Researcher in computational linguistics at Uppsala University's Department of Linguistics and Philology. She is affiliated with the Swedish National Language Bank and collaborates with researchers across multiple institutions, including the University of Gothenburg where she works with Lars Borin on corpus linguistics projects. Her academic work bridges computational methods with historical language analysis. Dr. Pettersson's research focuses on the intersection of digital humanities and computational linguistics, specializing in the processing and analysis of historical texts. Her work spans multiple domains including natural language processing for historical documents, historical cryptology, corpus development, and linguistic analysis of diachronic language change. She has made significant contributions to Swedish historical linguistics through her development of specialized resources and tools. Her publication record demonstrates a consistent trajectory of innovation in historical text processing, with recent work focusing on medieval scribal habits, named entity recognition in 19th century Swedish, rhetorical structure analysis of historical petitions, and historical cryptanalysis. These publications reveal a progression from foundational work on spelling normalization to increasingly sophisticated applications of NLP techniques to historical documents across multiple centuries. Dr. Pettersson has developed significant linguistic resources including the Swedish Diachronic Corpus and the HistCorp collection of historical corpora and tools. These resources have become essential for researchers working on historical Swedish language and provide standardized datasets for computational analysis of language change over time. Her collaborative work extends to international projects like the DECRYPT initiative for historical manuscript decryption and the development of specialized databases for historical ciphers. Through these projects, she has established herself as a key figure in the application of computational methods to historical linguistic materials and cryptological challenges.

پروفایل رسمی دانشگاه

Ji Young Kimمشاهده پروفایل

استادیار

University of California, Los AngelesUnited States

Ji Young Kim is an Assistant Professor in the Department of Spanish and Portuguese at UCLA's College of Letters and Science, specializing in heritage language phonology. Her research examines Spanish heritage speakers in the United States, focusing on perception and production of speech sounds amid language shift to English. Her primary research interests include heritage language phonology, bilingual speech perception, phonetic variation in heritage speakers, and the intersection of Latine/x/a/o identity with language attitudes. She investigates how extra-linguistic factors influence phonological development in heritage speakers, particularly examining the elusive 'heritage accent' through prosodic and segmental analysis. Her publication trends reveal deep engagement with heritage speaker phonetics across multiple dimensions: prosodic features (lexical stress, uptalk, focus marking), segmental production (trills, taps, palatal obstruents), and methodological innovations in linguistic landscape analysis. Recent work increasingly incorporates individual differences (autism quotient scores) and sociolinguistic frameworks to explain variation. Kim teaches graduate courses including SPAN202A Phonology, SPAN209 Spanish Dialectology, and multiple heritage language phonology seminars, alongside undergraduate courses on Spanish varieties and linguistic landscapes.

پروفایل رسمی دانشگاه

Johanna Gerlachمشاهده پروفایل

استاد

University of GenevaSwitzerland

Johanna Gerlach is a Professor at the Faculty of Translation and Interpretation at the University of Geneva, affiliated with the TIM/ISSCO research group. With an extensive publication record spanning from 2010 to 2025, she has established herself as a leading researcher in the field of medical translation technology and accessible healthcare communication. Her research focuses on developing innovative translation systems that bridge communication gaps in medical settings, particularly through her work on the BabelDr platform and PROPICTO project. Dr. Gerlach's work spans multiple dimensions of accessible communication including speech-to-pictograph translation systems, sign language production for healthcare, and multilingual medical communication solutions for emergency departments. Her research demonstrates a strong commitment to improving healthcare accessibility for non-native speakers and people with communication difficulties. Analysis of her recent publications (2023-2025) reveals a clear trend toward practical implementation of translation technologies in real-world healthcare settings, with particular emphasis on emergency medicine contexts. Her work integrates computational linguistics, machine learning, and human-centered design to create accessible communication tools that address critical gaps in multilingual healthcare delivery. The research spans both contemporary medical communication challenges and historical text processing applications. Dr. Gerlach has supervised 3 academic works and maintains an active research program with numerous ongoing projects including UNI-ACCESS (focusing on web accessibility for higher education institutions) and PASSAGE (addressing Swiss German TV content subtitling). Her collaborations span multiple disciplines including medical informatics, computational linguistics, and accessibility studies.

پروفایل رسمی دانشگاه

Gertjan van Noordمشاهده پروفایل

استاد

University of GroningenNetherlands

Professor Gertjan van Noord is affiliated with the University of Groningen , working in the Language Technology group under the Faculty of Arts . His research focuses on computational linguistics , dependency parsing , natural language processing , and machine translation , particularly for morphologically rich languages .

پروفایل رسمی دانشگاه

Delphine Bernhardمشاهده پروفایل

مدرس

University of StrasbourgFrance

Delphine Bernhard is a Lecturer in Computer Science at the Faculty of Languages, University of Strasbourg, since September 2011. She serves as head of the computer science department at the Faculty of Languages and co-head of the Master's degree in Language Technologies since 2016. Her research focuses on natural language processing, text mining, and lexical resource creation for under-resourced languages like Alsatian dialects. Institution: University of Strasbourg Academic Unit: Faculty of Languages Department: Computer Science Role: Lecturer & Department Head Teaching: Databases for CAWEB Master's program Her research explores natural language processing for under-resourced languages , particularly focusing on Alsatian dialects . Key areas include POS tagging , syntactic annotation , lexical resource development , and language revitalization through digital tools. She works on corpus creation , parallel corpora , and machine learning adaptation for regional language processing . Delphine Bernhard's publications demonstrate expertise in computational dialectology , low-resource language processing , linguistic annotation , and regional language preservation . Her work spans POS tagging , dependency parsing , emotion analysis in theater , and metadata management for regional languages of France . She contributes to the RESTAURE and DIVITAL projects, focusing on computational processing for regional languages . Her work includes FAIR corpus creation , spelling normalization , and lexicon development for Alsatian dialects . She explores cohesive features for text readability and develops crowdsourcing solutions for language resource bottlenecks .

پروفایل رسمی دانشگاه

Robert Apsimonمشاهده پروفایل

مدرس ارشد

Lancaster UniversityUnited Kingdom

Dr. Robert Apsimon is a Senior Lecturer in Electronic Engineering at Lancaster University's School of Engineering. He previously conducted postgraduate research at CERN from 2012 to 2014 before joining Lancaster in 2014 as a Postdoctoral Research Associate (PDRA). His current affiliations include the RF Engineering of Accelerators at Lancaster (REAL) research group. He has held teaching positions at the LU/BJTU joint campus in Weihai, China since 2018. Robert earned his MPhys degree from Balliol College, University of Oxford in 2007, followed by a D.Phil. in feedback electronics at the same institution. His research interests focus on advanced RF engineering applications in particle accelerators and medical physics, including high-power RF systems, radiotherapy optimization, nonlinear beam dynamics, and broadband acceleration techniques. His projects span foundational and applied research: as Principal Investigator for CERN's AWAKE experiment (2020-2027), he explores proton-driven plasma wakefield acceleration. He leads the JLab-funded EIC project (2023-2027), mentors students in quantum engineering, and collaborates on the STELLA initiative (2024-2025) to develop high-reliability radiotherapy linear accelerators. Notable collaborations include STFC Impact Acceleration Account projects (2021-2022) and contributions to Cockcroft Phase 4 (2021-2025), enhancing accelerator technology for medical and scientific applications. Robert supervises 9 postgraduate research students, including Alexander Spelling. His work emphasizes practical solutions for accelerator design challenges, beam instability mitigation, and medical application advancements. No scientific awards are explicitly listed in the provided information.

پروفایل رسمی دانشگاه

Andreas van Cranenburghمشاهده پروفایل

استادیار

University of GroningenNetherlands

Dr. Andreas van Cranenburgh is an Assistant Professor of Digital Humanities and Information Sciences at the University of Groningen, Faculty of Arts. His work focuses on computational linguistics, statistical parsing, and computational literary studies, with expertise in information science, language & linguistics, and artificial intelligence. He leads projects on historical text normalization, authorship attribution, and narrative analysis frameworks like the GOLEM Triple Store. His research integrates NLP techniques with literary analysis, addressing topics such as gender bias in literary prizes, coreference resolution in Dutch literature, and psycholinguistic applications in speech disorder detection. He collaborates on corpora like OpenBoek and Dutch Novels 1800-2000, advancing digital humanities infrastructure. Notable contributions include developing Dutchcoref systems for literary text processing, exploring machine learning approaches to literary quality, and advancing graph-based narrative representations. His work bridges computational methods with humanistic inquiry, impacting both academic research and cultural heritage preservation.

پروفایل رسمی دانشگاه