Aspect Level Sentiment Classification with Deep Memory Network
By Duyu Tang, Bing Qin, Ting-Wei Liu. 2016
981 citations recorded by the source corpus.
We introduce a deep memory network for aspect level sentiment classification. Unlike feature-based SVM and sequential neural models such as LSTM, this approach explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect. Such importance degree and text representation are calculated with multiple computational layers, each of which is a neural attention model over an external memory. Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures. On both datasets we show that multiple computational layers could improve the performance. Moreover, our approach is also fast. The deep memory network with 9 layers is 15 times faster than LSTM with a CPU implementation.
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
- Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021, methodology): “To be consistent with existing research [59], sentences with conflict opinions about a single aspect are not used.”
- BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, methodology): “To be consistent with existing research (Tang et al., 2016), examples belonging to the conflict polarity are dropped due to a very small number of examples.”
- CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (2021, methodology): “To be consistent with the existing research (Tang et al., 2016), sentences with both positive and negative sentiments about an aspect are not used.”
- Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (2019, methodology): “Constructing neural network models over word sequences, such as CNNs (Kim, 2014; Johnson and Zhang, 2015), RNNs (Tang et al., 2016a) and Recurrent Convolutional Neural Networks (RC- NNs) (Lai et al., 2015), has achieved promising performances in sentiment analysis.”
- Aspect-based Financial Sentiment Analysis with Deep Neural Networks (2018, methodology): “As for aspect level sentiment classification, Tang et al. [12]”
- An Unsupervised Neural Attention Model for Aspect Extraction (2017, background): “, 2015), sentiment classification (Chen et al., 2016; Tang et al., 2016), and question answering (Hermann et al.”
- Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks (2019, methodology): “Later, various neural network-based methods became popular for this task (Tang et al., 2016b; Wang et al., 2016), as they do not require manual feature engineering.”
- Aspect Based Sentiment Analysis with Gated Convolutional Networks (2018, methodology): “TD-LSTM (Tang et al., 2016a) uses two LSTM networks to model the preceding and following contexts of the target to generate target-dependent representation for sentiment prediction.”
- End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification (2017, background): “, 2016], and aspect-level sentiment classification [Tang et al., 2016].”
- Deep learning for sentiment analysis: A survey (2018, background): “Tang et al. 76 introduced an end-to-end memory network for aspect level sentiment classification, which employs an attention mechanism with an external memory to capture the importance of each context word with respect to the given target aspect.”
- Multi-grained Attention Network for Aspect-Level Sentiment Classification (2018, methodology): “Previous works (Tang et al., 2016b; Chen et al., 2017) mainly employed the simple averaged aspect vector to learn the attention weights on the context words.”
- SentiLARE: Linguistic Knowledge Enhanced Language Representation for Sentiment Analysis (2019, methodology): “Since the number of the examples with the conflict sentiment label is rather small, we adopted the same setting as the existing work (Tang et al., 2016; Xu et al., 2019) and dropped these examples in the aspect term / category sentiment classification task.”
- Recurrent Attention Network on Memory for Aspect Sentiment Analysis (2017, methodology): “• MemNet (Tang et al., 2016): It applies attention multiple times on the word embeddings,”