Northern European Association for Language Technology (NEALT)
Selle valdkonna püsiv URIhttps://hdl.handle.net/10062/4116
Northern European Association for Language Technology (NEALT)
http://omilia.uio.no/nealt/
The three NEALT series are indeed principally online publications. However, it is perfectly possible for the author or organizer to produce and distribute printed volumes. For that reason NEALT provides a cover design.
Sirvi
Sirvi Northern European Association for Language Technology (NEALT) Pealkiri järgi
Nüüd näidatakse 1 - 20 1307
- 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 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 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.Kirje A grammatical analyser for Tokelau(University of Tartu Library, 2025-03) Trosterud, Trond; Vonen, Arnfinn Muruvik; Trosterud, Trond; Wiechetek, Linda; Pirinen, FlammieThis article will present a grammatical aunalyser, disambiguator and dependency analysis of Tokelau. The grammatical analyser is written as a finite-state transducer (FST), whereas the disambiguator and dependency analyser are written in Constraint Grammar (CG), both within the GiellaLT infrastructure. Contrary to most languages analyzed within this framework, Being a Polynesian language, Tokelau is a predominantly isolating language, with reduplication and affixation as the main morphological processes. The article will discuss how FST and CG deal with Polynesian languages.Kirje A linear time extension of deterministic pushdown automata(2009-05-13T11:54:48Z) Søgaard, Anders