arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.06910cs.CL
收藏

神经语言模型的属性归纳框架

A Property Induction Framework for Neural Language Models

Purdue University(普渡大学);University of Chicago(芝加哥大学)

Kanishka Misra, Julia Taylor Rayz, Allyson Ettinger

摘要:

从语言中获得的经验在多大程度上有助于我们的概念知识?对这个问题的计算探索揭示了强大的神经语言模型(LM)的能力-仅通过文本输入获得信息-编码和获取有关概念和属性的信息。为了扩展这条研究路线,我们提出了一个框架,使用神经网络语言模型(LM)来执行属性归纳-一项任务,其中人类将新的属性知识(具有籽骨)从一个或多个概念(知更鸟)推广到其他概念(麻雀,金丝雀)。在人类身上观察到的属性归纳模式为人类概念知识的性质和组织提供了相当多的线索。受此启发,我们使用我们的框架来探索LM的属性归纳,并发现它们表现出归纳偏好,以类别成员资格为基础来概括新的属性,这表明它们的表示存在分类偏见。

英文摘要:

To what extent can experience from language contribute to our conceptual knowledge? Computational explorations of this question have shed light on the ability of powerful neural language models (LMs) -- informed solely through text input -- to encode and elicit information about concepts and properties. To extend this line of research, we present a framework that uses neural-network language models (LMs) to perform property induction -- a task in which humans generalize novel property knowledge (has sesamoid bones) from one or more concepts (robins) to others (sparrows, canaries). Patterns of property induction observed in humans have shed considerable light on the nature and organization of human conceptual knowledge. Inspired by this insight, we use our framework to explore the property inductions of LMs, and find that they show an inductive preference to generalize novel properties on the basis of category membership, suggesting the presence of a taxonomic bias in their representations.

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。

↑