About this collection

Recent Submissions

  • Bio-SimVerb and Bio-SimLex: wide-coverage evaluation sets of word similarity in biomedicine. 

    Chiu, Hon Wing; Pyysalo, Sampo; Vulić, Ivan; Korhonen, Anna-Leena (BioMed Central, 2018-02-05)
    Background: Word representations support a variety of Natural Language Processing (NLP) tasks. The quality of these representations is typically assessed by comparing the distances in the induced vector spaces against human ...
  • Investigating the cross-lingual translatability of VerbNet-style classification 

    Majewska, Olga; Vulić, I; McCarthy, D; Huang, Yan; Murakami, A; Laippala, V; Korhonen, Anna-Leena (Paradigm Press, 2017-10-20)
    VerbNet – the most extensive online verb lexicon currently available for English – has proved useful in supporting a variety of NLP tasks. However, its exploitation in multilingual NLP has been limited by the fact that ...
  • L’expression des procès spatiaux causatifs chez les apprenants francophones du chinois : pousser ou entrer ? 

    Arslangul, A; Hendriks, Henriette Petronella; Hickmann, M; Demagny, AC
    The present study examines French adult learners’ expressions of caused motion events in Chinese as a second language using the frameworks proposed by Talmy (1985, 1991, 2000). Productions are elicited by means of animated ...
  • Dependency parsing of learner English 

    Huang, Yan; Murakami, Akira; Alexopoulou, Theodora; Korhonen, Anna-Leena
    Current syntactic annotation of large-scale learner corpora mainly resorts to “standard parsers” trained on native language data. Understanding how these parsers perform on learner data is important for downstream research ...

View more