OpenAI 发布 GPT-2:无监督预训练实现多任务通用能力
原标题:Better language models and their implications
95AI 研判分
OpenAI 推出大规模无监督语言模型 GPT-2,在多项基准测试中达到 SOTA。该模型无需特定任务微调,即可执行阅读理解、翻译、问答及摘要等复杂任务,确立了“预训练+零样本/少样本”的新范式。
报道正文
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.