Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms

By Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, Xiaokui Xiao. AAAI Conference on Artificial Intelligence, 2017

410 citations recorded by the source corpus.

The task of aspect and opinion terms co-extraction aims to explicitly extract aspect terms describing features of an entity and opinion terms expressing emotions from user-generated texts. To achieve this task, one effective approach is to exploit relations between aspect terms and opinion terms by parsing syntactic structure for each sentence. However, this approach requires expensive effort for parsing and highly depends on the quality of the parsing results. In this paper, we offer a novel deep learning model, named coupled multi-layer attentions. The proposed model provides an end-to-end solution and does not require any parsers or other linguistic resources for preprocessing. Specifically, the proposed model is a multi-layer attention network, where each layer consists of a couple of attentions with tensor operators. One attention is for extracting aspect terms, while the other is for extracting opinion terms. They are learned interactively to dually propagate information between aspect terms and opinion terms. Through multiple layers, the model can further exploit indirect relations between terms for more precise information extraction. Experimental results on three benchmark datasets in SemEval Challenge 2014 and 2015 show that our model achieves state-of-the-art performances compared with several baselines.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/786d1ca11bfd95d8c845ef4a90b2d55092c2fb2f

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. Lei Shu
4. B. Liu
5. Philip S. Yu
6. Lidong Bing
7. Zixuan Ke
8. Wai Lam

Citations in the corpus

• Aspect Sentiment Quad Prediction as Paraphrase Generation (2021, background): “…2018; Ma et al., 2019), detecting the mentioned aspect category (Zhou et al., 2015; Bu et al., 2021), and predicting the sentiment polarity, given either an aspect term (Wang et al., 2016; Huang and Carley, 2018; Zhang and Qian, 2020) or an aspect category (Ruder et al., 2016; Hu et al., 2019a).”
• 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…”
• Deep learning for sentiment analysis: A survey (2018, neutral): “84”
• An Introductory Survey on Attention Mechanisms in NLP Problems (2018, background): “ representation space, which can be easily constructed by directly stacking together multiple single dimensional representations. As an example of 2D attention in aspect and opinion terms extraction (Wang et al. 2017), given a sequence of hidden representation of tokens V = fv ig, an aspect prototyp”
• Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, background): “Another related task – target and opinion span co-extraction (Qiu et al., 2011; Liu et al., 2013, 2014, 2015; Wang et al., 2017; Xu et al., 2018; Dai and Song, 2019) is also often regarded as a sequence labeling problem.”
• Data Poisoning Attacks on Federated Machine Learning (2020, background): “on [1]. Among these applications, the reliability or security of the machine learning system has been a great concern, including adversaries [10], [19]. For example, for product recommendation system [16], researchers can either rely on public crowd-sourcing platform, e.g., Amazon Mechanical Turk or”
• Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review (2019, methodology): “Meanwhile, W. Wang et al. (2017) proposed a Coupled Multi-Layer Attention Model (CMLA) based on GRU for co-extracting of aspect and opinion terms.”
• ReEL: Review Aware Explanation of Location Recommendation (2018, background): “Though a dedicated community has been focusing on the extraction of such aspects and opinions [12, 45, 47], the recommendation domain can also use such aspect-based summarization to enhance and explain the generated recommendation.”
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction (2018, methodology): “…applied to learn better features for supervised aspect extraction, e.g., us-ing LSTM (Williams and Zipser, 1989; Hochre-iter and Schmidhuber, 1997; Liu et al., 2015) and attention mechanism (Wang et al., 2017; He et al., 2017) together with manual features (Poria et al., 2016; Wang et al., 2016).”