Andmebaasi logo
Valdkonnad ja kollektsioonid
Kogu ADA
Eesti
English
Deutsch
  1. Esileht
  2. Sirvi autori järgi

Sirvi Autor "Karlgren, Jussi" järgi

Tulemuste filtreerimiseks trükkige paar esimest tähte
Nüüd näidatakse 1 - 9 9
  • Tulemused lehekülje kohta
  • Sorteerimisvalikud
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Assembling a Balanced Corpus from the Internet
    (Copenhagen, Denmark, Center for Sprogteknologi, University of Copenhagen, Denmark, pp. 100--108, 1998) Dewe, Johan; Karlgren, Jussi; Bretan, Ivan; Maegaard, Bente
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Clustering Sentences – Making Sense of Synonymous Sentences
    (Stockholm, Sweden, Department of Linguistics, Computational Linguistics, Stockholm University, Sweden, pp. 143--154, 1994) Karlgren, Jussi; Gambäck, Björn; Samuelsson, Christer; Eklund, Robert
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Comparing Human and Machine Translations of Generative Language Model Evaluation Datasets
    (University of Tartu Library, 2025-03) de Vroe, Sander Bijl; Stampoulidis, George; Hakala, Kai; Rouhe, Aku; van Heeswijk, Mark; Karlgren, Jussi; Johansson, Richard; Stymne, Sara
    The evaluation of Large Language Models (LLMs) is one of the crucial current challenges in the field of Natural Language Processing (NLP) and becomes even more challenging in the multilingual setting. Since the majority of the community's benchmarks exist only in English, test sets are now being machine translated at scale into dozens of languages. This work explores the feasibility of that approach, comparing a Finnish machine translation (MT) of ARC-Challenge with a new human translated version. Our findings suggest that since absolute scores are fairly close and model size rankings are preserved, machine translation is adequate in this case. Surprisingly, however, the datasets reverse the order of base models compared to their chat-finetuned counterparts.
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Compound terms and their constituent elements in information retrieval
    (Joensuu, Finland, University of Joensuu, Finland, pp. 111--115, 2006) Karlgren, Jussi; Werner, Stefan
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Creating bilingual lexica using reference wordlists for alignment of monolingual semantic vector spaces
    (Joensuu, Finland, University of Joensuu, Finland, pp. 71--77, 2006) Holmlund, Jon; Sahlgren, Magnus; Karlgren, Jussi; Werner, Stefan
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Experiments to investigate the utility of nearest neighbour metrics based on linguistically informed features for detecting textual plagiarism
    (2011-05-10) Almquist, Per; Karlgren, Jussi
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Experiments to investigate the utility of nearest neighbour metrics based on linguistically informed features for detecting textual plagiarism
    (Riga, Latvia, Northern European Association for Language Technology (NEALT), pp. 271--274, 2011) Almquist, Per; Karlgren, Jussi; Pedersen, Bolette Sandford; Nešpore, Gunta; Skadiņa, Inguna
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    Inferring the location of authors from words in their texts
    (Vilnius, Lithuania, Linköping University Electronic Press, Sweden, pp. 211--218, 2015) Berggren, Max; Karlgren, Jussi; Östling, Robert; Parkvall, Mikael; Megyesi, Beáta
  • Laen...
    Pisipilt
    listelement.badge.dso-type Kirje ,
    New Measures to Investigate Term Typology by Distributional Data
    (Oslo, Norway, Linköping University Electronic Press, Sweden, pp. 311--319, 2013) Karlgren, Jussi; Oepen, Stephan; Hagen, Kristin; Johannessen, Janne Bondi

DSpace tarkvara autoriõigus © 2002-2025 LYRASIS

  • Teavituste seaded
  • Saada tagasisidet