OpenAI News·· 2019-02-14精选AI 评分93
OpenAI 发布 GPT-2 大规模生成式语言模型
Better language models and their implications
AI 导读
OpenAI 发布 GPT-2，这是一个拥有 15 亿参数的自回归语言模型。该模型在 800 万篇网页文本上训练，无需微调即可在多项任务中展现强大的零样本学习能力。
推荐理由
OpenAI 官方发布了基于 Transformer 架构的大规模生成式预训练模型，展示了零样本迁移能力。
原文
We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.
来源：OpenAI News · openai.com