Scientific and Creative Analogies in Pretrained Language Models
arxiv(2022)
摘要
This paper examines the encoding of analogy in large-scale pretrained language models, such as BERT and GPT-2. Existing analogy datasets typically focus on a limited set of analogical relations, with a high similarity of the two domains between which the analogy holds. As a more realistic setup, we introduce the Scientific and Creative Analogy dataset (SCAN), a novel analogy dataset containing systematic mappings of multiple attributes and relational structures across dissimilar domains. Using this dataset, we test the analogical reasoning capabilities of several widely-used pretrained language models (LMs). We find that state-of-the-art LMs achieve low performance on these complex analogy tasks, highlighting the challenges still posed by analogy understanding.
更多查看译文
关键词
creative analogies,language,models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要