Türkçe Dil Modellerinin Performans Karşılaştırması Performance Comparison of Turkish Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913330233344000 |
|---|---|
| author | Dogan, Eren Uzun, M. Egemen Uz, Atahan Seyrek, H. Emre Zeer, Ahmed Sevi, Ezgi Kesgin, H. Toprak Yuce, M. Kaan Amasyali, M. Fatih |
| author_facet | Dogan, Eren Uzun, M. Egemen Uz, Atahan Seyrek, H. Emre Zeer, Ahmed Sevi, Ezgi Kesgin, H. Toprak Yuce, M. Kaan Amasyali, M. Fatih |
| contents | The developments that language models have provided in fulfilling almost all kinds of tasks have attracted the attention of not only researchers but also the society and have enabled them to become products. There are commercially successful language models available. However, users may prefer open-source language models due to cost, data privacy, or regulations. Yet, despite the increasing number of these models, there is no comprehensive comparison of their performance for Turkish. This study aims to fill this gap in the literature. A comparison is made among seven selected language models based on their contextual learning and question-answering abilities. Turkish datasets for contextual learning and question-answering were prepared, and both automatic and human evaluations were conducted. The results show that for question-answering, continuing pretraining before fine-tuning with instructional datasets is more successful in adapting multilingual models to Turkish and that in-context learning performances do not much related to question-answering performances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17010 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Türkçe Dil Modellerinin Performans Karşılaştırması Performance Comparison of Turkish Language Models Dogan, Eren Uzun, M. Egemen Uz, Atahan Seyrek, H. Emre Zeer, Ahmed Sevi, Ezgi Kesgin, H. Toprak Yuce, M. Kaan Amasyali, M. Fatih Computation and Language Artificial Intelligence The developments that language models have provided in fulfilling almost all kinds of tasks have attracted the attention of not only researchers but also the society and have enabled them to become products. There are commercially successful language models available. However, users may prefer open-source language models due to cost, data privacy, or regulations. Yet, despite the increasing number of these models, there is no comprehensive comparison of their performance for Turkish. This study aims to fill this gap in the literature. A comparison is made among seven selected language models based on their contextual learning and question-answering abilities. Turkish datasets for contextual learning and question-answering were prepared, and both automatic and human evaluations were conducted. The results show that for question-answering, continuing pretraining before fine-tuning with instructional datasets is more successful in adapting multilingual models to Turkish and that in-context learning performances do not much related to question-answering performances. |
| title | Türkçe Dil Modellerinin Performans Karşılaştırması Performance Comparison of Turkish Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.17010 |