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

The field of natural language processing (NLP) is contemporaneous with computers.
Machine translation systems were developed as early as the 1950s, and the widespread …

This paper is a contribution to the discussion on compiling computational lexical resources
from conventional dictionaries. It describes the theoretical as well as practical problems that …

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 …

In this paper, we describe the first English–Hungarian parallel corpus annotated for light
verb constructions, which contains 14,261 sentence alignment units. Annotation principles …

One of the most time-consuming parts of an attorney's job is finding similar legal cases.
Categorization of legal documents by their subject matter can significantly increase the …

Headedness is an intriguing feature of language design. On the one hand, headedness
manifests itself very clearly; preposed relative clauses are visibly different from postposed …

In this thesis, a subtype of multiword expressions, namely, semi-compositional constructions
will be analyzed from the perspectives of theoretical and computational linguistics. Multiword …

This paper describes an approach based on word alignment on parallel corpora, which aims
at facilitating the lexicographic work of dictionary building. Although this method has been …