Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis

By Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, Xiaokui Xiao. Conference on Empirical Methods in Natural Language Processing, 2016

387 citations recorded by the source corpus.

In aspect-based sentiment analysis, extracting aspect terms along with the opinions being expressed from user-generated content is one of the most important subtasks. Previous studies have shown that exploiting connections between aspect and opinion terms is promising for this task. In this paper, we propose a novel joint model that integrates recursive neural networks and conditional random fields into a unified framework for explicit aspect and opinion terms co-extraction. The proposed model learns high-level discriminative features and double propagate information between aspect and opinion terms, simultaneously. Moreover, it is flexible to incorporate hand-crafted features into the proposed model to further boost its information extraction performance. Experimental results on the SemEval Challenge 2014 dataset show the superiority of our proposed model over several baseline methods as well as the winning systems of the challenge.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/1c72d8090f281f58d5b141a3917e341250ab4c8c

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. Bing Liu
2. Hu Xu
3. B. Liu
4. Lei Shu
5. Philip S. Yu
6. Zixuan Ke
7. Shuai Wang
8. Lidong Bing

Citations in the corpus

• Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms (2017, methodology): “Our motivation is similar to (Qiu et al. 2011; Wang et al. 2016) for exploiting aspect-opinion relations.”
• An Unsupervised Neural Attention Model for Aspect Extraction (2017, methodology): “More recently, different neural models (Yin et al., 2016; Wang et al., 2016) were proposed to automatically learn features for CRF-based aspect extraction.”
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction (2018, methodology): “Further, (Wang et al., 2016, 2017; Li and Lam, 2017) also proposed aspect and opinion terms co-extraction via a deep network.”
• Deep learning for sentiment analysis: A survey (2018, background): “Wang et al.(83) further proposed a joint model integrating RNN and Conditional Random Fields (CRF) to co-extract aspects and opinion terms or expressions.”
• A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, methodology): “[141] proposed a novel model of recursive neural conditional random field (RNCRF) by integrating recursive neural networks based on the dependency tree of the sentence and conditional random fields into a unified framework.”
• Personalized machine learning for robot perception of affect and engagement in autism therapy (2018, background): “, object and scene recognition (63, 64) and sentiment analysis (65)), it has not been explored before in the context of robot perception for use in autism therapy.”
• Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis (2019, background): “…linked to aspect terms refers to ATC which attracts a heated research popularity (Dong 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…”
• 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).”
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, background): “Recently, supervised deep learning models dominate both tasks (Wang et al., 2016, 2017; Xu et al., 2018a; Tang et al., 2016; He et al., 2018) and many of these models use handcrafted features, lexicons, and complicated neural network architectures to remedy the insufficient training examples from…”
• Relational Graph Attention Network for Aspect-based Sentiment Analysis (2020, background): “Most recent efforts (Wang et al., 2016b; Li et al., 2017; Ma et al., 2017; Fan et al., 2018) resort to assorted attention mechanisms to achieve this goal and have reported appealing results.”