Heroes，Villains，and Victims，and GPT-3：Automated Extraction of Character Roles Without训练数据
Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data
ETH Zurich（苏黎世联邦理工学院）；Cornell University（康奈尔大学）
摘要：
本文展示了如何在没有训练数据的情况下使用大规模预训练语言模型从叙事文本中提取人物角色。在zero-shot问答提示下，GPT-3可以识别不同领域的英雄、恶棍和受害者：报纸文章、电影情节摘要和政治演讲。
英文摘要：
This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, villain, and victim in diverse domains: newspaper articles, movie plot summaries, and political speeches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
