The Acquisition of Anaphora by Simple Recurrent Networks
The Acquisition of Anaphora by Simple Recurrent Networks
复制标题
通过简单循环网络获取 Anaphora
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
W. Badecker
中科院分区：
文献类型：
--
作者：
R. Frank;D. Mathis;W. Badecker
本文将简单循环网络（SRN；Elman 1991、1993）应用于为反身和代词回指分配解释的任务。这项任务要求对句法结构比以前探索的更加精细的敏感性。从定量角度来看，SRN 的表现相当不错。然而，它们实现这种性能的方式在关键方面与目标语法不同：（i）线性 N-V 反身/代词序列影响 SRN 的解释，即使没有相关的结构关系，也会产生与人类不同的错误； (ii) SRN 的表示区分句子类型，抑制结构泛化； (iii) SRN 对照应依赖条件的了解无法推广到新的词汇项。这些结果不仅对 SRN 作为语言学习模型的可行性产生了重要影响，而且对神经网络泛化的系统性也产生了重要影响（Hadley 1994；Marcus 1998）。
This article applies Simple Recurrent Networks (SRNs; Elman 1991, 1993) to the task of assigning an interpretation to reflexive and pronominal anaphora. This task demands more refined sensitivity to syntactic structure than has been previously explored. Measured quantitatively, SRNs perform quite well. However, the way in which they achieve such performance diverges in key respects from the target grammar: (i) linear N-V-reflexive/pronoun sequences affect the SRN's interpretations, even without a relevant structural relation, yielding errors unlike those made by humans; (ii) the SRN's representations distinguish sentence types, inhibiting structural generalization; (iii) the SRN's knowledge of the conditions on anaphoric dependencies fails to generalize to novel lexical items. These results have important consequences not only for the viability of SRNs as models of language learning but also for the systematicity of generalization in neural networks (Hadley 1994; Marcus 1998).
句子处理过程中词汇访问的语义便利。
DOI：
10.1037//0278-7393.15.5.791
发表时间：
1989
期刊：
Journal of experimental psychology. Learning, memory, and cognition
影响因子：
--
作者：
Duffy,SA;Henderson,JM;Morris,RK
通讯作者：
Morris,RK
DOI：
10.1037//0278-7393.28.4.748
发表时间：
2002-07-01
影响因子：
2.6
作者：
Badecker, W;Straub, K
通讯作者：
Straub, K