Pregled bibliografske jedinice broj: 1200901
A General Framework for Detecting Metaphorical Collocations
A General Framework for Detecting Metaphorical Collocations // Proceedings of the LREC 2022 workshop on 18th Workshop on Multiword Expressions (MWE 2022) / Bhatia, Archna ; Cook, Paul ; Taslimipoor, Shiva ; Garcia, Marcos ; Ramisch, Carlos (ur.).
Pariz: European Language Resources Association (ELRA), 2022. str. 3-8 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1200901 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A General Framework for Detecting Metaphorical
Collocations
Autori
Brkić Bakarić, Marija ; Načinović Prskalo, Lucia ; Popović, Maja
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the LREC 2022 workshop on 18th Workshop on Multiword Expressions (MWE 2022)
/ Bhatia, Archna ; Cook, Paul ; Taslimipoor, Shiva ; Garcia, Marcos ; Ramisch, Carlos - Pariz : European Language Resources Association (ELRA), 2022, 3-8
ISBN
979-10-95546-90-0
Skup
18th Workshop on Multiword Expressions (MWE 2022) ; LREC2022
Mjesto i datum
Pariz, Francuska, 20.06.2022. - 26.06.2022
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
metaphorical collocations, classification, gold standard, significant relations, evaluation framework
Sažetak
This paper aims at identifying a specific set of collocations known under the term metaphorical collocations. In this type of collocations, a semantic shift has taken place in one of the components. Since the appropriate gold standard needs to be compiled prior to any serious endeavour to extract metaphorical collocations automatically, this paper first presents the steps taken to compile it, and then establishes appropriate evaluation framework. The process of compiling the gold standard is illustrated on one of the most frequent Croatian nouns, which resulted in the preliminary relation significance set. With the aim to investigate the possibility of facilitating the process, frequency, logDice, relation, and pretrained word embeddings are used as features in the classification task conducted on the logDicebased word sketch relation lists. Preliminary results are presented.
Izvorni jezik
Engleski
Znanstvena područja
Informacijske i komunikacijske znanosti
POVEZANOST RADA
Projekti:
HRZZ-IP-2020-02-6319 - Metaforičke kolokacije – sintagmatske sveze između semantike i pragmatike (METAKOL) (Stojić, Aneta, HRZZ - 2020-02) ( CroRIS)
Ustanove:
Fakultet informatike i digitalnih tehnologija, Rijeka