论文标题
注意机制是否具有人类阅读的特征？情感分类任务的观点
Does Attention Mechanism Possess the Feature of Human Reading? A Perspective of Sentiment Classification Task
论文作者
论文摘要
[目的]要理解句子的含义，人类可以专注于句子中的重要单词，这反映了我们的眼睛在不同的凝视时间或时间呆在每个单词上。因此，一些研究利用眼睛跟踪值来优化深度学习模型中的注意力机制。但是这些研究缺乏解释这种方法的合理性。需要探索注意力机制是否具有人类阅读的这一特征。 [设计/方法/方法]我们对情感分类任务进行了实验。首先，我们从两个开源的眼睛追踪语料库中获得了令人眼前一亮的值，以描述人类阅读的特征。然后，从情感分类模型中学到了每个句子的机器注意值。最后，进行了比较以分析机器注意值和眼睛跟踪值。 [发现]通过实验，我们发现注意机制可以集中于重要词，例如形容词，副词和情感词，这对于判断情感分类任务的句子情感很有价值。它具有人类阅读的特征，重点是阅读时的句子中的重要单词。由于注意力机制的学习不足，有些单词被错误地集中了。眼睛跟踪值可以帮助注意机制纠正此错误并改善模型性能。 [原创性/价值]我们的研究不仅为研究使用眼睛追踪值来优化注意力机制的研究提供了合理的解释，而且还为注意力机制的解释性提供了新的灵感。
[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize the attention mechanism in deep learning models. But these studies lack to explain the rationality of this approach. Whether the attention mechanism possesses this feature of human reading needs to be explored. [Design/methodology/approach] We conducted experiments on a sentiment classification task. Firstly, we obtained eye-tracking values from two open-source eye-tracking corpora to describe the feature of human reading. Then, the machine attention values of each sentence were learned from a sentiment classification model. Finally, a comparison was conducted to analyze machine attention values and eye-tracking values. [Findings] Through experiments, we found the attention mechanism can focus on important words, such as adjectives, adverbs, and sentiment words, which are valuable for judging the sentiment of sentences on the sentiment classification task. It possesses the feature of human reading, focusing on important words in sentences when reading. Due to the insufficient learning of the attention mechanism, some words are wrongly focused. The eye-tracking values can help the attention mechanism correct this error and improve the model performance. [Originality/value] Our research not only provides a reasonable explanation for the study of using eye-tracking values to optimize the attention mechanism, but also provides new inspiration for the interpretability of attention mechanism.
