论文标题
分析方法：口语神经模型中语音学的情况
Analyzing analytical methods: The case of phonology in neural models of spoken language
论文作者
论文摘要
鉴于NLP和语音处理系统的分析技术的快速开发，很少进行系统研究来比较每种方法的优势和缺点。作为朝这个方向发展的一步，我们研究了语言神经网络模型中语音学的案例。我们使用两种常用的分析技术，诊断分类器和表示相似性分析，以量化神经激活模式在多大程度上编码音素和音素序列。我们操纵可能影响分析结果的两个因素。首先，我们通过比较从训练有素的模型和随机定量模型中提取的神经激活来研究学习的作用。其次，我们通过探测与几毫秒语音信号相对应的局部激活来检查激活的时间范围，以及在整个话语中汇集的全局激活。我们得出的结论是，与随机初始化模型的报告分析结果至关重要，并且全球范围的方法倾向于产生更一致的结果，我们建议它们用作对局部SCOPE诊断方法的补充。
Given the fast development of analysis techniques for NLP and speech processing systems, few systematic studies have been conducted to compare the strengths and weaknesses of each method. As a step in this direction we study the case of representations of phonology in neural network models of spoken language. We use two commonly applied analytical techniques, diagnostic classifiers and representational similarity analysis, to quantify to what extent neural activation patterns encode phonemes and phoneme sequences. We manipulate two factors that can affect the outcome of analysis. First, we investigate the role of learning by comparing neural activations extracted from trained versus randomly-initialized models. Second, we examine the temporal scope of the activations by probing both local activations corresponding to a few milliseconds of the speech signal, and global activations pooled over the whole utterance. We conclude that reporting analysis results with randomly initialized models is crucial, and that global-scope methods tend to yield more consistent results and we recommend their use as a complement to local-scope diagnostic methods.
