EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Can a Transformer Model Learn Sublexical Groups in Korean Like Us?

Stanley Nam

Japanese/Korean Linguistics · 31.07.2026 · 32 (1)

DOI: 10.5070/j7.66638 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Japanese/Korean Linguistics, online erschienen am 31.07.2026. Verfasst von Stanley Nam. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study examined whether the selectivity of Korean L-Tensification (LT) extends to nonce words. LT applies only to a subset of eligible words, and this selective application has conventionally been attributed to Sino-Korean (SK) etymology. As an alternative, this study tested whether phonotactic patterns condition LT application. Forty-three speakers and a transformer model trained only on phonemic input-output pairs were tested on the same 144 nonce words, constructed to reflect SK, non-SK, or neutral phonotactics. LT application was quantified using acoustic measures for speakers and confidence scores for the transformer model. Both speakers and the model applied LT selectively. For speakers, non-SK phonotactics suppressed LT in plosive targets, whereas SK phonotactics promoted LT in affricate targets under specific structural conditions. However, the transformer diverged from the speakers, with both phonotactic manipulations lowering LT confidence. These results support a phonotactic contribution to LT selectivity, while the speaker-model divergence motivates future research.

Zitieren

APA

Nam, S. (2026). Can a Transformer Model Learn Sublexical Groups in Korean Like Us?. Japanese/Korean Linguistics, 32(1). https://doi.org/10.5070/j7.66638

Vancouver

Nam S. Can a Transformer Model Learn Sublexical Groups in Korean Like Us?. Japanese/Korean Linguistics. 2026;32(1). doi:10.5070/j7.66638

BibTeX
@article{Nam2026,
  author = {Nam, Stanley},
  title = {Can a Transformer Model Learn Sublexical Groups in Korean Like Us?},
  journal = {Japanese/Korean Linguistics},
  year = {2026},
  volume = {32},
  number = {1},
  doi = {10.5070/j7.66638}
}
Kostenlos starten →