• Areas of interest: Second Language Acquisition, computational syntax, dependency parsing, grammar engineering, cross-lingual approaches
• Current position: PhD student at Språkbanken Text (Department of Swedish, Multilingualism, Language Technology, University of Gothenburg) (see also my employee page)
• Supervisors: Elena Volodina and Dana Dannélls
• Contact: arianna.masciolini@gu.se

Scientific publications

• Arianna Masciolini, Andrew Caines, Orphée De Clercq, Joni Kruijsbergen, Murathan Kurfalı, Ricardo Muñoz Sánchez, Elena Volodina, and Robert Östling. The MultiGEC-2025 shared task on Multilingual Grammatical Error Correction at NLP4CALL. In Ricardo Muñoz Sánchez, David Alfter, Elena Volodina, and Jelena Kallas, editors, Proceedings of the 14th Workshop on Natural Language Processing for Computer Assisted Language Learning, pages 1-33, Tallinn, Estonia, March 2025. University of Tartu Library [pdf] [bibtex] [slides] [website]
• Arianna Masciolini, Andrew Caines, Orphée De Clercq, Joni Kruijsbergen, Murathan Kurfalı, Ricardo Muñoz Sánchez, Elena Volodina, Robert Östling, Kais Allkivi, Špela Arhar Holdt, Ilze Auzina, Roberts Darg̀is, Elena Drakonaki, Jennifer-Carmen Frey, Isidora Glišić, Pinelopi Kikilintza, Lionel Nicolas, Mariana Romanyshyn, Alexandr Rosen, Alla Rozovskaya, Kristjan Suluste, Oleksiy Syvokon, Alexandros Tantos, Despoina-Ourania Touriki, Konstantinos Tsiotskas, Eleni Tsourilla, Vassilis Varsamopoulos, Katrin Wisniewski, Aleš Žagar, and Torsten Zesch. Towards better language representation in Natural Language Processing - a multilingual dataset for text-level Grammatical Error Correction. International Journal of Learner Corpus Research, 2025 [full text] [bibtex] [website] [dataset] [supplementary report]
• Arianna Masciolini, Emilie Francis and Maria Irena Szawerna. Synthetic Error-Augmented Parsing of Swedish as a Second Language: Experiments with Word Order. In Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024, pages 43-49, Torino, Italy, 2024 [pdf] [bibtex] [code] [poster]
• Arianna Masciolini, Bootstrapping the Annotation of UD Learner Treebanks. In Proceedings of the 17th Workshop on Building and Using Comparable Corpora (BUCC) @ LREC-COLING 2024, pages 111-117, Torino, Italy, 2024 [pdf] [bibtex] [poster]
• Arianna Masciolini and Márton A. Tóth (equal contributions). STUnD: ett Sökverktyg för Tvåspråkiga Universal Dependencies-trädbanker. In Proceedings of the Huminfra Conference (HiC 2024), pages 95-109, Gothenburg, Sweden, 2024 [pdf] [bibtex] [code] [slides]
• Arianna Masciolini, Elena Volodina, and Dana Dannélls. Towards automatically extracting morphosyntactical error patterns from L1-L2 parallel dependency treebanks. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 585-597, Toronto, Canada, 2023 [pdf] [bibtex] [code] [poster] [slides] [video]
• Arianna Masciolini. A query engine for L1-L2 parallel dependency treebanks. In The 24rd Nordic Conference on Computational Linguistics, 2023 [pdf] [bibtex] [code] [slides]
• Arianna Masciolini. Building a multilingual AWE tool for L2 learners: challenges and ideas. In LIVE and LEARN-Festschrift in honor of Lars Borin, 2022 [pdf] [bibtex]
• Arianna Masciolini and Aarne Ranta. Grammar-based concept alignment for domain-specific Machine Translation. In Proceedings of the 7th International Workshop on Controlled Natural Language (CNL 2020/21), 2021 [pdf] [bibtex] [code] [slides]

Other writings

• Rapport från LREC-COLING (report on the Nationella Språkbanken website)
• Språkbanken Students at LREC-COLING 2024 (joint blog post with Ricardo Muñoz Sánchez on the (blog post on the Språkbanken Text blog)
• Korp tips and tricks: using CQP labels to search for dependency structures (blog post on the Språkbanken Text blog)

Teaching

Starting in 2019, I’ve been involved in several programming and language technology courses at the University of Gothenburg and at the Chalmers University of technology:

• LT2214 Computational Syntax (co-teacher)
• LT2001 Introduction to programming (co-teacher). For the 2025 edition of the course, I designed a small collection of Python exercises for Language Technology students
• LI2020 Syntax 2 (co-teacher)
• DAT455 Introduktion till Programmering i Python (co-course responsible)
• DAT515/DIT515 Advanced programming in Python (co-teacher)
• DIT143 Functional Programming (teaching assistant)

I am also a recurrent speaker in the ongoing “Data Plumbers’ corner” seminar series organized by the Laboratorio Sperimentale del Dipartimento di Lingue, Letterature e Culture Moderne (LILEC) of the University of Bologna.

Talks

Aside from paper presentations, I have given the following talks and special topic lectures:

• UD as an annotation standard for learner language - a use case on L2 Swedish. Special topic lecture in the context of the Computational Syntax course at the University of Gothenburg, Sweden, on May 26, 2025 [slides]
• MultiGEC-2025: a Multilingual Grammatical Error Correction shared task. Joint presentation with Ricardo Muñoz Sánchez at the Mini-workshop on Language learning, Multilinguality and Grammatical Error Correction, organized as part of the “Högre seminarium” of the Department of Swedish, Multilingualism, Language Technology of the University of Gothenburg (Gothenburg, Sweden) on December 16, 2024 [slides]
• STUnD: a Search Tool for (parallel) Universal Dependencies treebanks. Oral presentation at the 2024 workshop of Applications on Universal Dependencies, co-located with the 2024 Swedish Language Technology Conference (SLTC 2024) (Linköping, Sweden), on November 29, 2024 [slides]
• Cross-lingual approaches to computational SLA: the potential of Universal Dependencies. Halfway PhD seminar given at the “Högre seminarium” of the Department of Swedish, Multilingualism, Language Technology of the University of Gothenburg (Gothenburg, Sweden) on October 21, 2024 [slides]
• Universal Dependencies meets Second Language Acquisition: the case of Swedish. Project presentation at the PhD student session of the CLARIN Annual Conference 2024 (Barcelona, Spain) on October 16, 2024 [poster]
• SweLL-UD: a treebank of L2 Swedish essays. Project presentation at the 1st UniDive training school (Chișinău, Moldova) on July 8, 2024 [poster]
• Applications of UD analysis: syntactic queries, cross-linguistic comparisons and language learning. Joint special topic lecture with Aarne Ranta in the context of the Computational Syntax course at the University of Gothenburg, Sweden, on April 8, 2024 [slides]
• Dependency grammar and Universal Dependencies: an introduction and annotation exercise. Special topic lecture in the context of the Syntax 2 course at the University of Gothenburg, Sweden, on March 4, 2024 [slides]
• Python in Natural Language Processing. Special topic lecture in the context of the Advanced Programming in Python course at the Computer Science and Engineering department of the Chalmers University of Technology/University of Gothenburg, Sweden, on December 5, 2023 [slides and code]
• Feedback for language learners with UD and GF. Invited talk at the 8th Grammatical Framework Summer School (Tampere, Finland) on August 22, 2023 [slides]
• Artificiell intelligens och maskininlärning. Special topic lecture in the context of the Introduktion till Programmering i Python summer course at the Chalmers University of Technology (online), on July 31, 2023. [slides]
• UD-based analysis of grammatical errors in L2 texts. PhD planning seminar given at the “Högre seminarium” of the Department of Swedish, Multilingualism, Language Technology of the University of Gothenburg (Gothenburg, Sweden) on April 3, 2023 [slides]
• A gentle introduction to Argument Mining. Joint seminar with Anna Lindahl, Ricardo Muñoz Sánchez and Stian Rødven-Eide. Presented at CLASP (Gothenburg, Sweden) on October 21, 2022 [slides]
• Concept Alignment for Multilingual Machine Translation. Invited talk at the 7th Grammatical Framework Summer School (online) on August 4, 2021 [slides] [video]

Datasets

I am one of the core contributors to the MultiGEC dataset for text-level Multilingual Grammatical Error Correction.

Events

• I am the main organizer of the MultiGEC-2025 shared task on Multilingual text-level Grammatical Error Correction, whose results will be presented at the 14th NLP4CALL workshop, co-located with the NoDaLiDa/Baltic-HLT conference in Tallin, Estonia on March 5, 2024
• I was one of the organizers of the 2024 workshop of Applications on Universal Dependencies, co-located with the 2024 Swedish Language Technology Conference (SLTC 2024), on November 29, 2024.

Reviewing

I have reviewed for the following venues:

• the 11th Italian Conference on Computational Linguistics (CLiC-it 2025)
• the Journal of Contemporary Educational Studies / Sodobna pedagogika
• the 2024 and 2025 editions of the Workshop on Innovative Use of NLP for Building Educational Applications (BEA)
• the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
• the 2022 and 2025 editions of the Workshop on Natural Language Processing for Computer-Assisted Language Learning (NLP4CALL)
• the 2025 edition of the RESOURCEFUL Workshop on RESOURCEs and representations For Under-resourced Languages