论文标题
反复出现的babling：评估从有限输入数据中获得语法的获取
Recurrent babbling: evaluating the acquisition of grammar from limited input data
论文作者
论文摘要
复发性神经网络（RNN）已被证明可以从原始语言输入中捕获语法的各个方面。但是，在以前的大多数实验中，学习是通过不切实际的语料库进行的，这并不能反映孩子会暴露的数据的类型和数量。本文通过培训长期的短期记忆网络（LSTM）对儿童定向输入的一个大小的子集来纠正这种状况。随着时间的流逝，使用一种新方法来分析网络的行为，该方法包括量化模型生成的输出中语法抽象的水平（其“ Babbling”），与已接触到的语言相比。我们表明，LSTM确实抽象了学习的新结构。
Recurrent Neural Networks (RNNs) have been shown to capture various aspects of syntax from raw linguistic input. In most previous experiments, however, learning happens over unrealistic corpora, which do not reflect the type and amount of data a child would be exposed to. This paper remedies this state of affairs by training a Long Short-Term Memory network (LSTM) over a realistically sized subset of child-directed input. The behaviour of the network is analysed over time using a novel methodology which consists in quantifying the level of grammatical abstraction in the model's generated output (its "babbling"), compared to the language it has been exposed to. We show that the LSTM indeed abstracts new structuresas learning proceeds.
