Sirvi Autor "Tiedemann, Jörg" järgi

Nüüd näidatakse 1 - 20 70

listelement.badge.access-status Avatud juurdepääs ,
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, Sara
Fine-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.
listelement.badge.access-status Avatud juurdepääs ,
A modernised version of the Glossa corpus search system
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 251--254, 2017) Nøklestad, Anders; Hagen, Kristin; Bondi Johannessen, Janne; Kosek, Michał; Priestley, Joel; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
A Multilingual Entity Linker Using PageRank and Semantic Graphs
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 87--95, 2017) Södergren, Anton; Nugues, Pierre; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
A System for Identifying and Exploring Text Repetition in Large Historical Document Corpora
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 330--333, 2017) Vesanto, Aleksi; Ginter, Filip; Salmi, Hannu; Nivala, Asko; Salakoski, Tapio; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Acoustic Model Compression with MAP adaptation
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 65--69, 2017) Leino, Katri; Kurimo, Mikko; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Aligning phonemes using finte-state methods
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 56--64, 2017) Koskenniemi, Kimmo; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Analyzing the Effect of Linguistic Instructions on Paraphrase Generation
(University of Tartu Library, 2025-03) Vahtola, Teemu; Hu, Songbo; Creutz, Mathias; Korhonen, Anna; Vulić, Ivan; Tiedemann, Jörg; Johansson, Richard; Stymne, Sara
Recent work has demonstrated that large language models can often generate fluent and linguistically correct text, adhering to given instructions. However, to what extent can they execute complex instructions requiring knowledge of fundamental linguistic concepts and elaborate semantic reasoning? Our study connects an established linguistic theory of paraphrasing with LLM-based practice to analyze which specific types of paraphrases LLMs can accurately produce and where they still struggle. To this end, we investigate a method of analyzing paraphrases generated by LLMs prompted with a comprehensive set of systematic linguistic instructions. We conduct a case study using GPT-4, which has shown strong performance across various language generation tasks, and we believe that other LLMs may face similar challenges in comparable scenarios. We examine GPT-4 from a linguistic perspective to explore its potential contributions to linguistic research regarding paraphrasing, systematically assessing how accurately the model generates paraphrases that adhere to specified transformation rules. Our results suggest that GPT-4 frequently prioritizes simple lexical or syntactic alternations, often disregarding the transformation guidelines if they overly complicate the primary task.
listelement.badge.access-status Avatud juurdepääs ,
Boosting Neural Machine Translation from Finnish to Northern Sámi with Rule-Based Backtranslation
(Reykjavik, Iceland (Online), Linköping University Electronic Press, Sweden, pp. 351--356, 2021) Aulamo, Mikko; Virpioja, Sami; Scherrer, Yves; Tiedemann, Jörg; Dobnik, Simon; Øvrelid, Lilja
listelement.badge.access-status Avatud juurdepääs ,
Can We Create a Tool for General Domain Event Analysis?
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 192--201, 2017) Orasmaa, Siim; Kaalep, Heiki-Jaan; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Coreference Resolution for Swedish and German using Distant Supervision
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 46--55, 2017) Wallin, Alexander; Nugues, Pierre; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Creating register sub-corpora for the Finnish Internet Parsebank
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 152--161, 2017) Laippala, Veronika; Luotolahti, Juhani; Kyröläinen, Aki-Juhani; Salakoski, Tapio; Ginter, Filip; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Cross-lingual Learning of Semantic Textual Similarity with Multilingual Word Representations
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 211--215, 2017) Bjerva, Johannes; Östling, Robert; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Cross-Lingual Syntax: Relating Grammatical Framework with Universal Dependencies
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 322--325, 2017) Ranta, Aarne; Kolachina, Prasanth; Hallgren, Thomas; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Data Collection from Persons with Mild Forms of Cognitive Impairment and Healthy Controls - Infrastructure for Classification and Prediction of Dementia
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 172--182, 2017) Kokkinakis, Dimitrios; Lundholm Fors, Kristina; Björkner, Eva; Nordlund, Arto; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Dep_search: Efficient Search Tool for Large Dependency Parsebanks
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 255--258, 2017) Luotolahti, Juhani; Kanerva, Jenna; Ginter, Filip; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Docforia: A Multilayer Document Model
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 226--230, 2017) Klang, Marcus; Nugues, Pierre; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Dozens of Translation Directions or Millions of Shared Parameters? Comparing Two Types of Multilinguality in Modular Machine Translation
(University of Tartu Library, 2023-05) Boggia, Michele; Grönroos, Stig-Arne; Loppi, Niki Andreas; Mickus, Timothee; Raganato, Alessandro; Tiedemann, Jörg; Vázquez, Raúl
listelement.badge.access-status Avatud juurdepääs ,
Evaluation of language identification methods using 285 languages
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 183--191, 2017) Jauhiainen, Tommi; Lindén, Krister; Jauhiainen, Heidi; Tiedemann, Jörg; Tahmasebi, Nina
listelement.badge.access-status Avatud juurdepääs ,
Experiences in Building the Let’s MT! Portal on Amazon EC2
(Oslo, Norway, Linköping University Electronic Press, Sweden, pp. 11--11, 2013) Tiedemann, Jörg; Oepen, Stephan; Hagen, Kristin; Johannessen, Janne Bondi
listelement.badge.access-status Avatud juurdepääs ,
Exploring Properties of Intralingual and Interlingual Association Measures Visually
(Gothenburg, Sweden, Association for Computational Linguistics, pp. 314--317, 2017) Graën, Johannes; Bless, Christof; Tiedemann, Jörg; Tahmasebi, Nina