Transformation Networks for Target-Oriented Sentiment Classification

By Xin Li, Lidong Bing, Wai Lam, Bei Shi. Annual Meeting of the Association for Computational Linguistics, 2018

474 citations recorded by the source corpus.

Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the state-of-the-art performance. After re-examining the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this classification task, we propose a new model that achieves new state-of-the-art results on a few benchmarks. Instead of attention, our model employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RNN layer. Between the two layers, we propose a component which first generates target-specific representations of words in the sentence, and then incorporates a mechanism for preserving the original contextual information from the RNN layer.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/48a2661c7fb56cb762fe541304c5785d793e5a0f

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. Lidong Bing
2. Wenxuan Zhang
3. Wai Lam
4. Xin Li
5. Chenliang Li
6. Donghong Ji
7. Yangfeng Ji
8. Rui Wang

Citations in the corpus

• Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “• TNet-LF [57] adopts CNN to handle target-level sentiment classification and preserve and strengthen the informative part of contexts for the specific aspect.”
• Transfer Capsule Network for Aspect Level Sentiment Classification (2019, background): “In recent years, a number of deep learning methods have been proposed for aspect-level sentiment classification (ASC) tasks (Dong et al., 2014; Vo and Zhang, 2015; Tang et al., 2016; Wang et al., 2016a; Ma et al., 2017; Li et al., 2018; Ma et al., 2018; Wang et al., 2018a).”
• Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis (2019, unknown): “…et al. 2014; Tang, Qin, and Liu 2016; Nguyen and Shirai 2015; Wang et al. 2016b; Ma et al. 2017; Tay, Luu, and Hui 2017; Ma, Peng, and Cambria 2018; Hazarika et al. 2018; Li et al. 2018a; Wang et al. 2018; Xue and Li 2018; He et al. 2018; Peng et al. 2018; Bailin and Lu 2018; Li et al. 2019b).”
• Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2019, background): “, 2013), product recommendation (Chelliah and Sarkar, 2017), and sentiment analysis (Li et al., 2018; Zhao et al., 2018a).”
• Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, methodology): “…been proposed to implicitly model the semantic relation of an aspect and its context to capture the opinion expression component (Wang et al., 2016; Tang et al., 2016a,b; Ma et al., 2017; Chen et al., 2017; Fan et al., 2018; Huang et al., 2018; Gu et al., 2018; Li et al., 2018a; Tan et al., 2019).”
• A survey of the recent architectures of deep convolutional neural networks (2019, background): “In one of the previous studies, Transformation network (Jaderberg et al. 2015; Li et al. 2018) also exploited the idea of attention in a simple way by incorporating it with convolution block, but the main problem was that attention modules in Transformation network are fixed and cannot adapt to chan”
• Exploiting BERT for End-to-End Aspect-based Sentiment Analysis (2019, background): “, 2014, 2015, 2016) but re-prepared in Li et al. (2019a). The statistics are summarized in Table 3.”
• Relational Graph Attention Network for Aspect-based Sentiment Analysis (2020, methodology): “• Other recent methods: GCAE (Xue and Li, 2018), JCI (Wang et al., 2018) and TNET (Li et al., 2018).”
• Attentional Encoder Network for Targeted Sentiment Classification (2019, background): “, 2017) or to transform sentence representations according to target words (Li et al., 2018).”
• Improving the Interpretability of Neural Sentiment Classifiers via Data Augmentation (2019, methodology): “Sentiment analysis is one of the most widely-used applications of language technology, impacting both industry (Howard and Ruder, 2018; Li et al., 2018; Chen et al., 2016) and other NLP research topics (Feldman, 2013; Pang et al., 2002; Liu, 2012).”
• Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, background): “…to predicting sentiment polarity for a given target (Dong et al., 2014; Chen et al., 2017; Xue and Li, 2018; Wang and Lu, 2018; Wang et al., 2018; Li et al., 2018a; Peng et al., 2018; Xu et al., 2020) or joint extraction of targets as well as sentiment associated with each target (Mitchell et…”
• Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “…of baselines and state-of-the-art alternatives, including LSTM, MemNet (Tang et al., 2016b), AOA (Huang et al., 2018), IAN (Ma et al., 2017), TNetLF (Li et al., 2018), CAPSNet (Chen and Qian, 2019), Transfer-CAPS (Chen and Qian, 2019), TGBERT (Gao et al., 2019), AS-CNN (Zhang et al., 2019) and…”
• Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (2019, methodology): “where F(·) is a function assigning position weights, widely adopted by previous works (Li et al., 2018; Tang et al., 2016b; Chen et al., 2017), for augmenting the importance of context words close to the aspect.”
• A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, methodology): “In the combination of CNNs and RNNs, ConvNet-RNN networks with the cascaded fusion [230,283] or the ensemble strategy [215] have been proposed for FER, by simultaneously capturing textural and temporal information.”
• Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree (2019, methodology): “86 TNet (Li et al., 2018a) 80.”