🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Listing issues in NLG evaluations turned into a 25 page survey! In “Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text”, Thibault Sellam Elizabeth Clark and I cover 250+ papers. 📄Link: arxiv.org/abs/2202.06935 Want to learn more?👇

Introducing the 540 billion parameter Pathways Language Model. Trained on two Cloud #TPU v4 pods, it achieves state-of-the-art performance on benchmarks and shows exciting capabilities like mathematical reasoning, code writing, and even explaining jokes. goo.gle/3j6eMnK

Had the change to collaborate on this Large Language Model latest work at Google. The capabilities of this model are impressive and for NLG, it shows the first glimpses of few-shot generation on long context tasks.

QAmeleon: Multilingual QA with Only 5 Examples abs: arxiv.org/abs/2211.08264

Can we scale QA models to low resource languages with just a few-examples? We propose to use pre-trained language models (PLMs) under few-shot settings to build large multilingual training data sets. QAmeleon: Multilingual QA with Only 5 Examples: arxiv.org/abs/2211.08264