Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction

By Hu Xu, B. Liu, Lei Shu, Philip S. Yu. Annual Meeting of the Association for Computational Linguistics, 2018

358 citations recorded by the source corpus.

One key task of fine-grained sentiment analysis of product reviews is to extract product aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using deep learning. Unlike other highly sophisticated supervised deep learning models, this paper proposes a novel and yet simple CNN model employing two types of pre-trained embeddings for aspect extraction: general-purpose embeddings and domain-specific embeddings. Without using any additional supervision, this model achieves surprisingly good results, outperforming state-of-the-art sophisticated existing methods. To our knowledge, this paper is the first to report such double embeddings based CNN model for aspect extraction and achieve very good results.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/9a91e3a88632ef68e4932d4a49321dd9b0311062

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. Minlie Huang

Citations in the corpus

• Aspect Sentiment Quad Prediction as Paraphrase Generation (2021, background): “Early studies focus on the prediction of a single element such as aspect term extraction (Liu et al., 2015; Xu et al., 2018), as-”
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, methodology): “For AE, we choose SemEval 2014 Task 4 for laptop and SemEval-2016 Task 5 for restaurant to be consistent with (Xu et al., 2018a) and other previous works.”
• Lifelong Domain Word Embedding via Meta-Learning (2018, methodology): “Although some embeddings trained using large scale corpora are available [ Pen-nington et al. , 2014; Bojanowski et al. , 2016], they are often sub-optimal for domain-specific tasks [Bollegala et al. , 2015; Yang et al. , 2017; Xu et al. , 2018a; Xu et al. , 2018b].”
• SentiLARE: Linguistic Knowledge Enhanced Language Representation for Sentiment Analysis (2019, methodology): “…tasks, including SC-SNN (Chen et al., 2019), DRNN (Wang, 2018), ML (Sachan et al., 2019) for sentence-level sentiment classification, DE-CNN (Xu et al., 2018) for aspect term extraction, CDT (Sun et al., 2019a) for aspect term sentiment classification, TAN (Movahedi et al., 2019) for aspect…”
• 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.”
• Natural Language Processing Advancements By Deep Learning: A Survey (2020, background): “language model BERT [112], and employment of pre-trained embeddings [128].”