An NLP model that understands stories should be able to understand the characters in them. To support the development of neural models for this purpose, we construct a benchmark, Story2Personality. The task is to predict a movie character's MBTI or Big 5 personality types based on the narratives of the character. Experiments show that our task is challenging for the existing text classification models, as none is able to largely outperform random guesses. We further proposed a multi-view model for personality prediction using both verbal and non-verbal descriptions, which gives improvement compared to using only verbal descriptions. The uniqueness and challenges in our dataset call for the development of narrative comprehension techniques from the perspective of understanding characters.
翻译:理解故事的NLP模型应该能够理解其中的字符。 为了支持为此开发神经模型, 我们构建了一个基准, “ 故事2个人性 ” 。 任务是根据字符的描述预测电影字符 MBTI 或大5个个个个性类型。 实验表明,我们的任务对现有文本分类模型具有挑战性, 因为没有人能够大大超过随机猜测。 我们还提议了一个多视角模型, 用于使用口头和非口头描述进行个性预测, 与仅使用口头描述相比,该模型有改进。 我们数据集的独特性和挑战要求从理解字符的角度发展叙述理解技术。