会员服务
Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics
Arxiv
0+阅读 · 2月19日
What Language is This? Ask Your Tokenizer
Arxiv
0+阅读 · 2月19日
Are LLMs Ready to Replace Bangla Annotators?
Arxiv
0+阅读 · 2月19日
Are LLMs Ready to Replace Bangla Annotators?
Arxiv
0+阅读 · 2月18日
CitiLink-Summ: Summarization of Discussion Subjects in European Portuguese Municipal Meeting Minutes
Arxiv
0+阅读 · 2月18日
Making Large Language Models Speak Tulu: Structured Prompting for an Extremely Low-Resource Language
Arxiv
0+阅读 · 2月17日
Under-resourced studies of under-resourced languages: lemmatization and POS-tagging with LLM annotators for historical Armenian, Georgian, Greek and Syriac
Arxiv
0+阅读 · 2月17日
Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition
Arxiv
0+阅读 · 2月4日
Layer-wise Swapping for Generalizable Multilingual Safety
Arxiv
0+阅读 · 2月13日
Towards Personalized Bangla Book Recommendation: A Large-Scale Multi-Entity Book Graph Dataset
Arxiv
0+阅读 · 2月12日
Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domains
Arxiv
0+阅读 · 2月9日
AmharicIR+Instr: A Two-Dataset Resource for Neural Retrieval and Instruction Tuning
Arxiv
0+阅读 · 2月10日
Compiler-Guided Inference-Time Adaptation: Improving GPT-5 Programming Performance in Idris
Arxiv
0+阅读 · 2月12日
MedVAR: Towards Scalable and Efficient Medical Image Generation via Next-scale Autoregressive Prediction
Arxiv
0+阅读 · 2月16日
VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars
Arxiv
0+阅读 · 2月9日
参考链接
微信扫码咨询专知VIP会员
Top