法国或西班牙或德国或法国:对非冗余冗余析取的神经账户
France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions
AI总结:
本文通过神经机制解释了非冗余冗余析取现象,揭示了上下文敏感语义解释的机制,并补充了现有符号分析。
摘要:
像“She will go to France or Spain, or perhaps to Germany or France.”这样的句子在形式上显得冗余,但在诸如“Mary will go to a philosophy program in France or Spain, or a mathematics program in Germany or France.”这样的上下文中却变得可接受。尽管这种现象通常被分析为使用符号形式表示,我们旨在提供一个基于人工神经机制的补充解释。我们首先展示了来自人类和大语言模型的新行为证据,证明这种看似非冗余性在不同上下文中都具有鲁棒性。然后我们展示,在语言模型中,冗余避免源于两个相互作用的机制:模型学会将上下文相关的信息绑定到重复的词项上,并且Transformer诱导头部会选择性地关注这些上下文许可的表示。我们主张这种神经解释有助于阐明上下文敏感语义解释的机制,并且补充了现有的符号分析。
英文摘要:
Sentences like "She will go to France or Spain, or perhaps to Germany or France." appear formally redundant, yet become acceptable in contexts such as "Mary will go to a philosophy program in France or Spain, or a mathematics program in Germany or France." While this phenomenon has typically been analyzed using symbolic formal representations, we aim to provide a complementary account grounded in artificial neural mechanisms. We first present new behavioral evidence from humans and large language models demonstrating the robustness of this apparent non-redundancy across contexts. We then show that, in language models, redundancy avoidance arises from two interacting mechanisms: models learn to bind contextually relevant information to repeated lexical items, and Transformer induction heads selectively attend to these context-licensed representations. We argue that this neural explanation sheds light on the mechanisms underlying context-sensitive semantic interpretation, and that it complements existing symbolic analyses.
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。