Pregledni rad

https://doi.org/10.31724/rihjj.49.1.1

Insights Into Automatic Extraction of Metaphorical Collocations

Marija Brkić Bakarić orcid.org/0000-0003-4079-4012 ; Fakultet informatike i digitalnih tehnologija, Sveučilište u Rijeci
Lucia Načinović Prskalo orcid.org/0000-0002-8832-2527 ; Fakultet informatike i digitalnih tehnologija, Sveučilište u Rijeci
Maja Matetić ; Fakultet informatike i digitalnih tehnologija, Sveučilište u Rijeci

Sažetak

Collocations have been the subject of much scientific research over the years. The focus of this research is on a subset of collocations, namely metaphorical collocations. In metaphorical collocations, a semantic shift has taken place in one of the components, i.e., one of the components takes on a transferred meaning. The main goal of this paper is to review the existing literature and provide a systematic overview of the existing research on collocation extraction, as well as the overview of existing methods, measures, and resources. The existing research is classified according to the approach (statistical, hybrid, and distributional semantics) and presented in three separate sections. The insights gained from existing research serve as a first step in exploring the possibility of developing a method for automatic extraction of metaphorical collocations. The methods, tools, and resources that may prove useful for future work are highlighted.

Ključne riječi

metaphorical collocations; automatic extraction; association measures; hybrid approaches; distributional semantics approaches; evaluation measures

Hrčak ID:

306555

URI

https://hrcak.srce.hr/306555

Datum izdavanja:

24.7.2023.

Podaci na drugim jezicima: hrvatski

Posjeta: 450 *