Target-Sensitive Memory Networks for Aspect Sentiment Classification

Abstract

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 targetsensitive memory networks (TMNs). Several alternative techniques are designed for the implementation of TMNs and their effectiveness is experimentally evaluated.

Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis

“…Table 4 provides all the experimental results. To enhance the persuasiveness of our experimental results, we also displayed the previously reported scores of MN (Wang et al, 2018) and TNet on the same data set. According to the experimental results, we can come to the following conclusions:…”

“…Datasets. We applied the proposed approach into MN (Tang et al, 2016b;Wang et al, 2018) and TNet-ATT ) (see Section 2), and conducted experiments on three benchmark datasets: LAPTOP, REST (Pontiki et al, 2014) and TWITTER (Dong et al, 2014). In our datasets, the target aspect of each sentence has been provided.…”

“…All hyper-parameters were tuned on 20% randomly held-out training data. Finally, we used F1-Macro and accuracy as our evaluation Model LAPTOP REST TWITTER Macro-F1 Accuracy Macro-F1 Accuracy Macro-F1 Accuracy MN (Wang et al, 2018) 62 (Wang et al, 2018;. * * and * means significant at p <0.01 and p <0.05 over the baselines (MN, TNet) on each test set, respectively.…”

“…Here we introduce some notations to facilitate subsequent descriptions: x= (x 1 , x 2 , ..., x N ) is the input sentence, t= (t 1 , t 2 , ..., t T ) is the given target aspect, y, y p ∈{Positive, Negative, Neutral} denote the ground-truth and the predicted sentiment, respectively. MN (Tang et al, 2016b;Wang et al, 2018). The framework illustration of MN is given in Figure 1.…”

Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis

“…Traditional machine learning methods for aspectbased sentiment analysis focus on extracting a set of features to train sentiment classifiers (Ding et al, 2009;Boiy and Moens, 2009;Jiang et al, 2011), which usually are labor intensive. With the development of deep learning technologies, neural attention mechanism (Bahdanau et al, 2014) has been widely adopted to address this task (Tang et al, 2015;Wang et al, 2016;Tang et al, 2016;Ma et al, 2017;Chen et al, 2017;Cheng et al, 2017;Li et al, 2018a;Wang et al, 2018a;Tay et al, 2018;Hazarika et al, 2018;Majumder et al, 2018;Fan et al, 2018;Wang et al, 2018b). Wang et al (2016) propose attention-based LSTM networks which attend on different parts of the sentence for different aspects.…”