TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Uludoğan, Gökçe, Balal, Zeynep Yirmibeşoğlu, Akkurt, Furkan, Türker, Melikşah, Güngör, Onur, Üsküdarlı, Susan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911364417585152
author Uludoğan, Gökçe
Balal, Zeynep Yirmibeşoğlu
Akkurt, Furkan
Türker, Melikşah
Güngör, Onur
Üsküdarlı, Susan
author_facet Uludoğan, Gökçe
Balal, Zeynep Yirmibeşoğlu
Akkurt, Furkan
Türker, Melikşah
Güngör, Onur
Üsküdarlı, Susan
contents The recent advances in natural language processing have predominantly favored well-resourced English-centric models, resulting in a significant gap with low-resource languages. In this work, we introduce the language model TURNA, which is developed for the low-resource language Turkish and is capable of both natural language understanding and generation tasks. TURNA is pretrained with an encoder-decoder architecture based on the unified framework UL2 with a diverse corpus that we specifically curated for this purpose. We evaluated TURNA with three generation tasks and five understanding tasks for Turkish. The results show that TURNA outperforms several multilingual models in both understanding and generation tasks, and competes with monolingual Turkish models in understanding tasks. TURNA is made available at https://huggingface.co/boun-tabi-LMG/TURNA .
format Preprint
id arxiv_https___arxiv_org_abs_2401_14373
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation
Uludoğan, Gökçe
Balal, Zeynep Yirmibeşoğlu
Akkurt, Furkan
Türker, Melikşah
Güngör, Onur
Üsküdarlı, Susan
Computation and Language
Artificial Intelligence
Machine Learning
The recent advances in natural language processing have predominantly favored well-resourced English-centric models, resulting in a significant gap with low-resource languages. In this work, we introduce the language model TURNA, which is developed for the low-resource language Turkish and is capable of both natural language understanding and generation tasks. TURNA is pretrained with an encoder-decoder architecture based on the unified framework UL2 with a diverse corpus that we specifically curated for this purpose. We evaluated TURNA with three generation tasks and five understanding tasks for Turkish. The results show that TURNA outperforms several multilingual models in both understanding and generation tasks, and competes with monolingual Turkish models in understanding tasks. TURNA is made available at https://huggingface.co/boun-tabi-LMG/TURNA .
title TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2401.14373