序列到序列网络学习反身回指的意义
Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora
摘要：
反身回指对语义解释提出了挑战：它们的意义依赖于上下文，似乎需要抽象变量。过去的工作对经常性网络应对这一挑战的能力提出了质疑。在本文中，我们探讨这个问题的背景下，英语的片段，结合了相关的排序的上下文变异。我们认为，序列到序列的架构与经常性的单位，并表明这种网络能够学习语义解释的反身回指概括到新的先行词。我们探索了注意力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，这可以通过两种方式来衡量：需要多少词汇支持来诱导抽象的反身意义（即，在训练过程中必须出现多少个不同的反身先行词），以及一个名词短语必须出现在什么样的语境中才能支持对这个名词短语的反身解释的泛化？
英文摘要：
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?
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。
