Target-Sensitive Memory Networks for Aspect Sentiment Classification
Target-Sensitive Memory Networks for Aspect Sentiment Classification
复制标题
DOI：
10.18653/v1/p18-1088
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Shuai Wang;S. Mazumder;B. Liu;Mianwei Zhou;Yi Chang
中科院分区：
文献类型：
--
作者：
Shuai Wang;S. Mazumder;B. Liu;Mianwei Zhou;Yi Chang
方面情感分类（ASC）是情感分析中的一项基本任务。给定一个方面/目标和一个句子，该任务对句子中目标上表达的情感极性进行分类。记忆网络（MN）最近已被用于这项任务，并取得了国家的最先进的成果。在MN中，注意机制在检测给定目标的情感上下文中起着至关重要的作用。然而，我们发现了一个重要的问题，目前的MN在执行ASC任务。简单地改进注意机制并不能解决这个问题，这个问题被称为目标敏感的情感，这意味着（检测到的）上下文的情感极性取决于给定的目标，并且它不能单独从上下文推断。为了解决这个问题，我们提出了目标敏感的内存网络（TMN）。几种替代技术的TMN的实施和他们的有效性进行了实验评估。
Aspect sentiment classification (ASC) is a fundamental task in sentiment analysis. Given an aspect/target and a sentence, the task classifies the sentiment polarity expressed on the target in the sentence. Memory networks (MNs) have been used for this task recently and have achieved state-of-the-art results. In MNs, attention mechanism plays a crucial role in detecting the sentiment context for the given target. However, we found an important problem with the current MNs in performing the ASC task. Simply improving the attention mechanism will not solve it. The problem is referred to as target-sensitive sentiment, which means that the sentiment polarity of the (detected) context is dependent on the given target and it cannot be inferred from the context alone. To tackle this problem, we propose the target-sensitive memory networks (TMNs). Several alternative techniques are designed for the implementation of TMNs and their effectiveness is experimentally evaluated.