Nominal compounds such as red wine and nut case display a continuum of compositionality,
with varying contributions from the components of the compound to its semantics. This article …

Distributional semantic models (DSMs) are often evaluated on artificial similarity datasets
containing single words or fully compositional phrases. We present a large-scale …

Word embeddings are a form of distributional semantics increasingly popular for
investigating lexical semantic change. However, typical training algorithms are probabilistic …

The stability of word embedding algorithms, ie, the consistency of the word representations
they reveal when trained repeatedly on the same data set, has recently raised concerns. We …

One of the most intriguing phenomena in human languages is the creation and use of
idiomatic expressions which defy all rules of logical composition. For instance, in Brazilian …

Nous décrivons une étude visant à repérer automatiquement des relations lexico-
sémantiques à partir de corpus spécialisés au moyen d'une méthode d'analyse …

Abstrakt (y) The article presents an exploratory study on the use of two specificity adjectives:
specific and particular in the corpus of British Academic Written English, with supplementary …

Les modèles de langue contextuels se sont rapidement imposés comme des outils
essentiels du Traitement Automatique des Langues. Néanmoins, certains travaux ont …

In the field of natural language processing and cognitive science, vector representations of
words (vector space models) play an increasingly important role. While much research is …

In recent decades there has been an increase in interest on methods for the automatic
construction of distributional thesauri from corpora. Efforts to systematically evaluate and …