Proceedings
Selle valdkonna püsiv URIhttps://hdl.handle.net/10062/4117
NEALT Proceedings Series
ISSN 1736-6305 (Online)
ISSN 1736-8197 (Print)
Series Editor-in-Chief: Mare Koit (until December 31, 2011)
Series Editorial Board: Lars Ahrenberg, Koenraad De Smedt, Kristiina Jokinen, Joakim Nivre, Patrizia Paggio, Vytautas Rudžionis
http://omilia.uio.no/nealt/
The NEALT Proceeding series publishes peer-reviewed proceedings of scientific events that have a thematic and geographical relation to the purposes of NEALT
Requests for publication can be sent to the editor-in-chief. Published proceedings must document the composition of the program committee, the review procedure, and the acceptance rate in the preface.
ISSN 1736-6305 (Online)
ISSN 1736-8197 (Print)
Series Editor-in-Chief: Mare Koit (until December 31, 2011)
Series Editorial Board: Lars Ahrenberg, Koenraad De Smedt, Kristiina Jokinen, Joakim Nivre, Patrizia Paggio, Vytautas Rudžionis
http://omilia.uio.no/nealt/
The NEALT Proceeding series publishes peer-reviewed proceedings of scientific events that have a thematic and geographical relation to the purposes of NEALT
Requests for publication can be sent to the editor-in-chief. Published proceedings must document the composition of the program committee, the review procedure, and the acceptance rate in the preface.
Sirvi
Sirvi Proceedings Pealkiri järgi
Nüüd näidatakse 1 - 20 1325
- Tulemused lehekülje kohta
- Sorteerimisvalikud
Kirje 14th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2025)(University of Tartu Library, 2025-03) Muñoz Sánchez, Ricardo; Alfter, David; Volodina, Elena; Kallas, JelenaKirje 1st Workshop on Ecology, Environment, and Natural Language Processing.(University of Tartu Library, 2025-03) Basile, Valerio; Bosco, Cristina; Grasso, Francesca; Ibrahim, Muhammad Okky; Skeppstedt, Maria; Stede, ManfredKirje 1st Workshop on Ecology, Environment, and Natural Language Processing. Proceedings of NLP4Ecology2025(University of Tartu Library, 2025-03-02) Basile, Valerio; Bosco, Cristina; Grasso, Francesca; Ibrahim, Muhammad Okky; Skeppstedt, Maria; Stede, ManfredKirje 24th Nordic Conference on Computational Linguistics (NoDaLiDa)(University of Tartu Library, 2023-05) Alumäe, Tanel, toimetaja; Fišel, Mark, toimetajaKirje A Caribbean Directory-based Encryption during the American War of Independence(Tartu University Library, 2025) Pierrot, Cécile; Chaline, Olivier; Damoiseau-Malraux, Gaspard; Mekhail, Paul; Perret, Ludovic; Antal, Eugen; Marák, PavolThe corpus of letters we are studying is located at the Archives Nationales d'Outre-Mer in Aix-en-Provence, France. These late 18th-century letters come from Saint Domingue (now Haiti), a French colony in the Caribbean Sea of which Bellecombe, the author, was governor. They were written in the context of the American War of Independence, in which France took part on the side of the Americans. We have reconstructed Bellecombe's correspondence with the Secretary of State for the Navy, in Versailles: the archives contain hundreds of letters in clear and three encrypted letters, including some clear/cipher pages that were our lever for reconstructing part of the key, and 96 % of the encrypted letter that was opaque at first. From a cryptanalytical point of view, Bellecombe used a directory-based encryption. The common use of this type of cipher in the 17th and 18th-century European countries raises the question of the method to be used (then as now!) to decode such messages.Kirje A categorization scheme for analyzing rules from a handbook of Swedish writing rules(2011-05-10) Foo, JodyKirje A character-based analysis of impacts of dialects on end-to-end Norwegian ASR(University of Tartu Library, 2023-05) Parsons, Phoebe; Kvale, Knut; Svendsen, Torbjørn; Salvi, GiampieroKirje A Collaborative Model of Treebank Development(2007-11-29T15:44:05Z) Bamman, David; Passarotti, Marco; Crane, Gregory; Raynaud, SavinaKirje A Collection of Question Answering Datasets for Norwegian(University of Tartu Library, 2025-03) Mikhailov, Vladislav; Mæhlum, Petter; Langø, Victoria Ovedie Chruickshank; Velldal, Erik; Øvrelid, Lilja; Johansson, Richard; Stymne, SaraThis paper introduces a new suite of question answering datasets for Norwegian; NorOpenBookQA, NorCommonSenseQA, NorTruthfulQA, and NRK-Quiz-QA. The data covers a wide range of skills and knowledge domains, including world knowledge, commonsense reasoning, truthfulness, and knowledge about Norway. Covering both of the written standards of Norwegian – Bokmål and Nynorsk – our datasets comprise over 10k question-answer pairs, created by native speakers. We detail our dataset creation approach and present the results of evaluating 11 language models (LMs) in zero- and few-shot regimes. Most LMs perform better in Bokmål than Nynorsk, struggle most with commonsense reasoning, and are often untruthful in generating answers to questions. All our datasets and annotation materials are publicly available.Kirje A Comparative Study of PEFT Methods for Python Code Generation(University of Tartu Library, 2025-03) Männistö, Johanna; Attieh, Joseph; Tiedemann, Jörg; Johansson, Richard; Stymne, SaraFine-tuning language models incurs high costs in training, inference and storage. Parameter-efficient fine-tuning (PEFT) methods have emerged as a more cost-effective alternative to full fine-tuning. However, limited work has compared different PEFT approaches for tasks like code generation. In this study, we examine the effect of various PEFT training methods on model performance in the task of Python code generation. We fine-tune four model families, ranging from 124M to 7B parameters, using three PEFT approaches alongside standard full fine-tuning. Our findings reveal that the effectiveness of each PEFT method varies with the model size and the corpus used.Kirje A comparison and combination of segmental and fixed-frame signal representations in NMF-based word recognition(2009-05-13T13:04:39Z) Räsänen, Okko; Driesen, JorisKirje A constraint grammar for Faroese(2009-11-14T21:43:41Z) Trosterud, TrondKirje A Dependency Constraint Grammar for Esperanto(2009-11-14T21:45:30Z) Bick, EckhardKirje A Diachronic View of Pronominal Reference in English(2008-11-14T15:44:37Z) Azuma, HiromiKirje A double-blind experiment on interannotator agreement: the case of dependency syntax and Finnish(2011-05-10) Voutilainen, Atro; Purtonen, TanjaKirje A Finite State Constraint Grammar Parser(2011-11-17) Peltonen, JanneKirje A Florentine ‘polyalphabetic’ cipher in the 15th century(Tartu University Library, 2025) Vito, Marco; Antal, Eugen; Marák, PavolThe 15th century in Italy was a period of revolution in cryptography. Leon Battista Alberti developed the first western polyalphabetic cipher, while the monoalphabetic system spread throughout the peninsula. The aim of this study is to present a never before published late medieval 15th-century Florentine polyalphabetic cipher, explain its functioning, and shed light on a system—specifically the polyalphabetic cipher—that, although seemingly unused during the 15th century, was in fact employed in Florentine diplomacy.Kirje A FrameNet for Danish(2011-05-09) Bick, EckhardKirje A Gold Standard for English–Swedish Word Alignment(2011-05-09) Holmqvist, Maria; Ahrenberg, LarsKirje A Grammar-Based Method for Instilling Empirical Dependency Structure in LLMs(University of Tartu Library, 2025-03) Torstensson, Olle; Holmström, Oskar; Trosterud, Trond; Wiechetek, Linda; Pirinen, FlammieWe investigate whether synthetic pretraining data generated from a formal grammar modeling syntactic dependencies can improve English language models. Building upon the structured pretraining data approach of Papadimitriou and Jurafsky (2023), we develop a grammar that more closely mirrors empirical dependency structures. Our results are negative – this type of pretraining significantly degrades model performance, with both our and their pretraining approach performing worse than no pretraining at all. We analyze potential explanations for these findings and discuss implications for future work on structured-data pretraining.