循环神经网络在语音同化与异化中的内在偏差
Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation
AI总结：
提出一种单循环层神经网络模型用于语音模式学习，其学习偏差能模拟人类实验结果，且无需非循环模型中所需的复杂特征表示。
摘要：
提出了一种用于语音模式学习的循环神经网络模型。该模型是一个具有单个循环层的相对简单的神经网络，其学习偏差能够模拟人类学习中观察到的偏差。单特征模式的学习速度快于双特征模式，且仅涉及元音或辅音的模式的学习速度快于涉及元音和辅音的模式，这与实验室学习实验的结果一致。在非循环模型中，捕捉这些偏差需要使用alpha特征或其他重复特征的表示，但使用循环神经网络则不需要这些复杂处理。
英文摘要：
A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary.
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。
