Gated Neural Networks for Targeted Sentiment Analysis

By Meishan Zhang, Duy-Tin Vo. AAAI Conference on Artificial Intelligence, 2016

295 citations recorded by the source corpus.

Targeted sentiment analysis classifies the sentiment polarity towards each target entity mention in given text documents. Seminal methods extract manual discrete features from automatic syntactic parse trees in order to capture semantic information of the enclosing sentence with respect to a target entity mention. Recently, it has been shown that competitive accuracies can be achieved without using syntactic parsers, which can be highly inaccurate on noisy text such as tweets. This is achieved by applying distributed word representations and rich neural pooling functions over a simple and intuitive segmentation of tweets according to target entity mentions. In this paper, we extend this idea by proposing a sentence-level neural model to address the limitation of pooling functions, which do not explicitly model tweet-level semantics. First, a bi-directional gated neural network is used to connect the words in a tweet so that pooling functions can be applied over the hidden layer instead of words for better representing the target and its contexts. Second, a three-way gated neural network structure is used to model the interaction between the target mention and its surrounding contexts. Experiments show that our proposed model gives significantly higher accuracies compared to the current best method for targeted sentiment analysis.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/688d8718e662d931d8c0ab1bfd03314c2ba711af

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

1. B. Liu
2. Shuai Wang
3. Bing Liu
4. Lei Zhang
5. Lidong Bing
6. Erik Cambria
7. Wai Lam
8. Xin Li

Citations in the corpus

• A survey on empathetic dialogue systems (2020, background): “A similar problem has been raised for emotion or sentiment classification [140, 141, 142], but has been missing in the context of dialogue systems.”
• Aspect Based Sentiment Analysis with Gated Convolutional Networks (2018, methodology): “Such models include Attention-based LSTM with Aspect Embedding (ATAE-LSTM) (Wang et al., 2016b) for ACSA; Target-Dependent Sentiment Classification (TD-LSTM) (Tang et al., 2016a), Gated Neural Networks (Zhang et al., 2016) and Recurrent Attention Memory Network (RAM) (Chen et al., 2017) for ATSA.”
• Transformation Networks for Target-Oriented Sentiment Classification (2018, background): “Similar to (Tang et al., 2016a), Zhang et al. (2016) develop a three-way gated neural network to model the interaction between the target and its surrounding contexts.”
• Deep learning for sentiment analysis: A survey (2018, methodology): “Considering the limitation of work by Dong et al. 68 and Vo and Zhang 69 , Zhang et al. 72 proposed a sentence level neural model to address the weakness of pooling functions, which do not explicitly model tweet-level semantics.”
• Stance Detection with Bidirectional Conditional Encoding (2016, background): “Bag-of-word baselines (BoWV, SVM-ngramscomb) achieve results comparable to the majority baseline (F1 of 0.2972), which shows how difficult the task is.”
• EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks (2017, methodology): “…suitable for handling time-series data like speech (Graves et al., 2013) or handwriting recognition (Graves, 2012; Graves and Schmidhuber, 2009), have also been used successfully for sentiment analysis (Ren et al., 2016; Liu et al., 2015; Tai et al., 2015; Tang et al., 2015; Zhang et al., 2016).”
• Target-Dependent Sentiment Classification With BERT (2019, background): “Convolutional Neural Networks (CNN), Recursive Neural Networks [6] and Gated Neural Networks [49] are used less frequently in aspect-level sentiment classification.”