Transformer-based architectures brought a breeze of change to Word Sense
Disambiguation (WSD), improving models' performances by a large margin. The fast …

The ability to correctly model distinct meanings of a word is crucial for the effectiveness of
semantic representation techniques. However, most existing evaluation benchmarks for …

Masked language models have quickly become the de facto standard when processing text.
Recently, several approaches have been proposed to further enrich word representations …

Abstract Information systems are increasingly making use of taxonomic knowledge about
words and entities. A taxonomic knowledge base may reveal that the Lago di Garda is a lake …

The article is an introduction to a major research project, which aims to identify how motion
events are encoded in the Estonian language. The main objective of the article is to find out …

The present study is an attempt in the development of semantic relations among the Punjabi
Shahmukhi verbs. Semantic relations are taken as a key part of the WordNet. The WordNet …

This article describes an ongoing workan experiment on anaphora resolution in Estonian
newspaper texts using Constraint Grammar (CG) rules. The personal, demonstrative and …

This paper introduces a new free and open-source linguistic resource for the Estonian
language—a computational description of the Estonian syntax and morphology …

Given that much of our knowledge is expressed in textual form, information systems are
increasingly dependent on knowledge about words and the entities they represent. This …

The present study intends to develop lexico-semantic relationships among Saraiki verbs. For
this purpose, the semantic relationships of the English WordNet model established by Miller …