| Naslov: | Mono- and cross-lingual evaluation of representation language models on less-resourced languages |
|---|
| Avtorji: | ID Ulčar, Matej (Avtor)
ID Žagar, Aleš (Avtor)
ID Armendariz, Carlos S. (Avtor)
ID Repar, Andraž, Institut "Jožef Stefan" (Avtor)
ID Pollak, Senja, Institut "Jožef Stefan" (Avtor)
ID Purver, Matthew, Institut "Jožef Stefan" (Avtor)
ID Robnik Šikonja, Marko (Avtor) |
|---|
| Datoteke: |  URL - Izvorni URL, za dostop obiščite https://www.sciencedirect.com/science/article/pii/S0885230825000774?via%3Dihub
 PDF - Predstavitvena datoteka, prenos (2,28 MB)
MD5: B4BE1F405393A7D919CA1A369BFD46BC
|
|---|
| Jezik: | Angleški jezik |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: |  IJS - Institut Jožef Stefan
|
|---|
| Povzetek: | The current dominance of large language models in natural language processing is based on their contextual awareness. For text classification, text representation models, such as ELMo, BERT, and BERT derivatives, are typically fine-tuned for a specific problem. Most existing work focuses on English; in contrast, we present a large-scale multilingual empirical comparison of several monolingual and multilingual ELMo and BERT models using 14 classification tasks in nine languages. The results show, that the choice of best model largely depends on the task and language used, especially in a cross-lingual setting. In monolingual settings, monolingual BERT models tend to perform the best among BERT models. Among ELMo models, the ones trained on large corpora dominate. Cross-lingual knowledge transfer is feasible on most tasks already in a zero-shot setting without losing much performance. |
|---|
| Ključne besede: | monolingual models, multilingual models, ELMo, BERT, corpus, cross-lingual datasets |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 03.09.2023 |
|---|
| Datum sprejetja članka: | 03.06.2025 |
|---|
| Datum objave: | 27.06.2025 |
|---|
| Založnik: | Elsevier |
|---|
| Leto izida: | 2026 |
|---|
| Št. strani: | 1-29 str. |
|---|
| Številčenje: | Vol. 95, [article no.] 101852 |
|---|
| Izvor: | Nizozemska |
|---|
| PID: | 20.500.12556/DiRROS-22874  |
|---|
| UDK: | 004.8 |
|---|
| ISSN pri članku: | 1095-8363 |
|---|
| DOI: | 10.1016/j.csl.2025.101852 |
|---|
| COBISS.SI-ID: | 241622275 |
|---|
| Avtorske pravice: | © 2025 The Authors. |
|---|
| Opomba: | Nasl. z nasl. zaslona;
Opis vira z dne 7. 7. 2025;
|
|---|
| Datum objave v DiRROS: | 07.07.2025 |
|---|
| Število ogledov: | 327 |
|---|
| Število prenosov: | 214 |
|---|
| Metapodatki: |    |
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
