BriefGPT.xyz
Feb, 2024
优质数据到文本生成用于严重资源不足的语言的开箱即用大型语言模型
High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models
HTML
PDF
Michela Lorandi, Anya Belz
TL;DR
大型语言模型可以在研究欠资源语言中通过数据到文本生成来弥补性能差距，但人工评估表明BLEU分数相比于英语有所下降，对于评估非任务特定系统其适用性存疑。
Abstract
The performance of
nlp methods
for severely
under-resourced languages
cannot currently hope to match the state of the art in
nlp methods
f
→