Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora
Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora
复制标题
DOI：
--
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
R. Frank;Jackson Petty
中科院分区：
文献类型：
--
作者：
R. Frank;Jackson Petty
反身回指对语义解释提出了挑战：它们的意义取决于上下文，在某种程度上似乎需要抽象变量。过去的工作对循环网络应对这一挑战的能力提出了质疑。在本文中，我们在一个包含相关类型语境变异的英语片段的背景下探讨了这个问题。我们考虑了具有循环单元的序列到序列结构，并表明这种网络能够学习反身回指的语义解释，并将其推广到新的先行词。我们探讨了注意机制和不同的循环单元类型对成功所需的训练数据类型的影响，通过两种方式来衡量：诱导一个抽象的反身意义需要多少词汇支持（即，在训练过程中必须出现多少不同的反身先行词），以及一个名词短语必须出现在什么语境中才能支持对这个名词短语的反身解释的概括？
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?