Lifelong Learning Memory Networks for Aspect Sentiment Classification

By Shuai Wang, Guangyi Lv, Sahisnu Mazumder, Geli Fei, Bing Liu. 2018

30 citations recorded by the source corpus.

Aspect sentiment classification (ASC) is a fundamental task in sentiment analysis. It aims at classifying the sentiment expressed on some target aspects/features of entities (e.g., products and services). Although a great deal of research has been done, this task remains to be very challenging. Recently, memory networks, a type of neural model, have been used for this task and have achieved state-of-the-art results. However, such neural models usually require a large amount of well-annotated training data for producing reasonably good results. Unfortunately, for the ASC task, the human-annotated data with aspect-level labels are scarce and costly to obtain. In this work, we aim to use big unlabeled data to help. The key idea is to make a memory network learn knowledge from the big unlabeled data (treated as past tasks) and use the learned knowledge to better guide its future task learning. To achieve this goal, we propose a novel lifelong learning approach that can automatically meta-mine knowledge from multiple past domains. In addition, a new model named lifelong learning memory network (L2MN) is proposed to incorporate the mined knowledge into its learning process, where two types of knowledge are involved, namely, aspect-sentiment attention and context-sentiment effect. Extensive experimental results using real-world review datasets demonstrate the effectiveness of our approach.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (2021, neutral): “Although there are also works using neural networks (Ke et al., 2020; Wang et al., 2018; Thrun, 1998; Silver et al., 2013), all of them (including those based on traditional learning methods) work on tasks that are very similar and thus there is almost no forgetting.”
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (2021, methodology): “Wang et al. (2018) used LL for ASC, but improved only the new task and did not deal with CF. Existing CL systems SRK (Lv et al., 2019), KAN (Ke et al., 2020b) and L2PG (Qin et al., 2020) are for document sentiment classiﬁcation, but not ASC.”
Continual Learning with Knowledge Transfer for Sentiment Classification (2021, methodology): “The work in [26, 29] uses LL for aspect-based sentiment analysis, which is an entirely different problem than document-level sentiment classification (SC) studied in this paper.”
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (2021, methodology): “L2PG (Qin et al., 2020) uses a neural network but improves only the new task learning for DSC. Wang et al. (2018) worked on ASC, but since they improve only the new task learning, they did not deal with CF.”
Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification (2021, background): “In parallel, there are several works devoted to improving the performance of sentiment classification in a continual learning scenario [7, 22, 37].”
Using the Past Knowledge to Improve Sentiment Classification (2020, background): “Wang et al. (2018) studied aspect level sentiment classiﬁcation, which is not the goal of L2PG.”