论文标题
序列到序列网络学习反射性图的含义
Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora
论文作者
论文摘要
反射性图表对语义解释提出了一个挑战：它们的含义取决于上下文，似乎需要抽象变量。过去的工作引起了人们对重复网络应对这一挑战的能力的怀疑。在本文中，我们在包含相关上下文可变性的英语片段的背景下探讨了这个问题。我们考虑使用复发单元的序列到序列体系结构，并表明此类网络能够学习反思性图谱的语义解释，以推广到新的前因。我们探讨了注意机制和不同的复发单元类型对成功的培训数据类型的影响，这些培训数据类型是通过两种方式来衡量的：需要多少词汇支持来诱导抽象的反思性含义（即在培训期间必须出现多少不同的反思性前对象），以及在支持这个noun noun phrrase的一般性诠释中必须出现哪些名词短语才能出现什么名词。
Reflexive anaphora present a challenge for semantic interpretation: their meaning varies depending on context in a way that appears to require abstract variables. Past work has raised doubts about the ability of recurrent networks to meet this challenge. In this paper, we explore this question in the context of a fragment of English that incorporates the relevant sort of contextual variability. We consider sequence-to-sequence architectures with recurrent units and show that such networks are capable of learning semantic interpretations for reflexive anaphora which generalize to novel antecedents. We explore the effect of attention mechanisms and different recurrent unit types on the type of training data that is needed for success as measured in two ways: how much lexical support is needed to induce an abstract reflexive meaning (i.e., how many distinct reflexive antecedents must occur during training) and what contexts must a noun phrase occur in to support generalization of reflexive interpretation to this noun phrase?
