顺序问题:幼儿语音的分布特性促进了语义表征的学习
Order matters: Distributional properties of speech to young children bootstraps learning of semantic representations
摘要:
一些研究者认为,语言的习得主要依赖于对语言输入的体验,而语言输入的复杂程度是递增的。我们开始使用一个简单的递归神经网络(SRN)来测试这个假设,该网络被训练用于预测CHILDES中的单词序列,CHILDES是一个针对儿童的500万单词的语音语料库。首先,我们证明了年龄排序的儿童表现出逐渐增加的语言复杂性。接下来,我们比较了在CHILDES上训练的两组SRN的性能,这两组SRN要么是按年龄排序的,要么不是。具体来说,我们评估了语法和语义结构的学习,并表明,年龄顺序输入的培训有利于语义的学习,但不是顺序结构。我们发现,当模型在去除了话语边界信息的输入上训练时,这种优势就被消除了。
英文摘要:
Some researchers claim that language acquisition is critically dependent on experiencing linguistic input in order of increasing complexity. We set out to test this hypothesis using a simple recurrent neural network (SRN) trained to predict word sequences in CHILDES, a 5-million-word corpus of speech directed to children. First, we demonstrated that age-ordered CHILDES exhibits a gradual increase in linguistic complexity. Next, we compared the performance of two groups of SRNs trained on CHILDES which had either been age-ordered or not. Specifically, we assessed learning of grammatical and semantic structure and showed that training on age-ordered input facilitates learning of semantic, but not of sequential structure. We found that this advantage is eliminated when the models were trained on input with utterance boundary information removed.
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。