分析方法：以口语神经模型中的语音为例（CS CL）---用户7095611

鉴于NLP和语音处理系统分析技术的快速发展，很少有系统的研究来比较每种方法的优缺点。作为朝这个方向迈出的一步，我们研究了语音在口语神经网络模型中的表现。我们使用两种常用的分析技术，诊断分类器和表征相似性分析，来量化神经激活模式在多大程度上编码音素和音素序列。我们操纵了两个影响分析结果的因素。首先，我们通过比较从训练模型和随机初始化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的语音信号相对应的局部激活和聚集在整个话语中的全局激活来检查激活的时间范围。我们的结论是，使用随机初始化的模型报告分析结果是至关重要的，全局范围方法往往会产生更一致的结果，我们建议将其用作局部范围诊断方法的补充。

原文题目：Analyzing analytical methods: The case of phonology in neural models of spoken language

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.

原文作者：Grzegorz Chrupała

原文地址：https://arxiv.org/abs/2004.07070