Multi-grained Attention Network for Aspect-Level Sentiment Classification

By Feifan Fan, Yansong Feng, Dongyan Zhao. Conference on Empirical Methods in Natural Language Processing, 2018

467 citations recorded by the source corpus.

We propose a novel multi-grained attention network (MGAN) model for aspect level sentiment classification. Existing approaches mostly adopt coarse-grained attention mechanism, which may bring information loss if the aspect has multiple words or larger context. We propose a fine-grained attention mechanism, which can capture the word-level interaction between aspect and context. And then we leverage the fine-grained and coarse-grained attention mechanisms to compose the MGAN framework. Moreover, unlike previous works which train each aspect with its context separately, we design an aspect alignment loss to depict the aspect-level interactions among the aspects that have the same context. We evaluate the proposed approach on three datasets: laptop and restaurant are from SemEval 2014, and the last one is a twitter dataset. Experimental results show that the multi-grained attention network consistently outperforms the state-of-the-art methods on all three datasets. We also conduct experiments to evaluate the effectiveness of aspect alignment loss, which indicates the aspect-level interactions can bring extra useful information and further improve the performance.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/6e279973506f42868590d88e4cc01e1c4febb034

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. Philip S. Yu
3. Wenxuan Zhang
4. Wai Lam
5. Xin Li
6. Hao Peng
7. Lichao Sun
8. Rui Wang

Citations in the corpus

• 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.”
• Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “[16] proposed a multiple fine-grained 75”
• A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “MGAN [80] presents a fine-grained attention mechanism with a coarse-grained attention mechanism to learn the word-level interaction between context and aspect.”
• Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, methodology): “Such datasets were all created based on the datasets originally released by SemEval (Pontiki et al., 2014, 2015, 2016; Fan et al., 2018).”
• Exploiting BERT for End-to-End Aspect-based Sentiment Analysis (2019, background): “…al., 2017; Liu and Zhang, 2017; Ma et al., 2017, 2018b; Majumder et al., 2018; Li et al., 2018; He et al., 2018; Xue and Li, 2018; Wang et al., 2018; Fan et al., 2018; Huang and Carley, 2018; Lei et al., 2019; Li et al., 2019b; Zhang et al., 2019) 2 , but the improvement of these models measured…”
• Attention in Natural Language Processing (2019, background): “[112], for instance, computed coarse-grained and fine-grained attention in parallel and combined the results into a single embedding.”
• Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR (2020, methodology): “As-pect is a complex phenomenon and an active area of NLP research (Reichart and Rappoport, 2010; Donatelli et al., 2018; Fan et al., 2018) and cognitive research (Tajiri et al., 2012; Lai et al., 2009).”
• Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, background): “To judge the sentiment of a particular aspect, previous studies (Wang et al., 2016; Tang et al., 2016a; Ma et al., 2017; Chen et al., 2017; Fan et al., 2018; Huang et al., 2018; Gu et al., 2018) have proposed various recurrent neural networks (RNNs) with attention mechanisms to generate aspect-speci”
• A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “MGAN [195] presents a fine-grained attention mechanism with a coarsegrained attention mechanism to learn the word-level interaction between context and aspect.”