High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models
The performance of NLP methods for severely under-resourced languages cannot currently hope to match the state of the art in NLP methods for well resourced languages. We explore the extent to which pretrained large language models (LLMs) can bridge this gap, via the example of data-to-text generation for Irish, Welsh, Breton and Maltese. We test LLMs on these under-resourced languages and English, in a range of scenarios. We find that LLMs easily set the state of the art for the under-resourced languages by substantial margins, as measured by both automatic and human evaluations. For all our languages, human evaluation shows on-a-par performance with humans for our best systems, but BLEU scores collapse compared to English, casting doubt on the metric's suitability for evaluating non-task-specific systems. Overall, our results demonstrate the great potential of LLMs to bridge the performance gap for under-resourced languages.
Code (1)
Tasks
Data-to-Text GenerationText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
Training generative models that can generate high-quality text with sufficient diversity is an important open problem for Natural Language Generation (NLG) community. Recently, generative adversarial models have been app…
Adversarial TextDiversityLanguage ModelingLanguage Modelling+2Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention
Recently, powerful Transformer architectures have proven superior in generating high-quality sentences. Nevertheless, these models tend to produce dull high-frequency phrases, severely hurting the diversity and novelty o…
AttributeDiversityText GenerationHunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation
Recent advances in video generation produce visually realistic content, yet the absence of synchronized audio severely compromises immersion. To address key challenges in video-to-audio generation, including multimodal d…
Audio GenerationVideo GenerationDual Diffusion Models for Multi-modal Guided 3D Avatar Generation
Generating high-fidelity 3D avatars from text or image prompts is highly sought after in virtual reality and human-computer interaction. However, existing text-driven methods often rely on iterative Score Distillation Sa…
Computational EfficiencyGDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
Dynamic Text-Attributed Graphs (DyTAGs), which intricately integrate structural, temporal, and textual attributes, are crucial for modeling complex real-world systems. However, most of the existing DyTAG datasets exhibit…
BenchmarkingGraph GenerationGraph Learning