# AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations

arXiv: https://arxiv.org/abs/2108.11656 · HTML: https://mlsanity.com/paper/2108.11656/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Visualizing and Measuring the Geometry of BERT](https://mlsanity.com/paper/1906.02715/) (2019)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT](https://mlsanity.com/paper/1911.03681/) (2019)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [CoLAKE: Contextualized Language and Knowledge Embedding](https://mlsanity.com/paper/2010.00309/) (2020)
- [Aspect Level Sentiment Classification with Deep Memory Network](https://mlsanity.com/paper/1605.08900/) (2016)
- [Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification](https://mlsanity.com/paper/1908.11860/) (2019)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking](https://mlsanity.com/paper/2003.05473/) (2020)
- [Transformation Networks for Target-Oriented Sentiment Classification](https://mlsanity.com/paper/1805.01086/) (2018)
- [Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa](https://mlsanity.com/paper/2104.04986/) (2021)
- [Multimodal Explanations by Predicting Counterfactuality in Videos](https://mlsanity.com/paper/1812.01263/) (2018)
- [A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction](https://mlsanity.com/paper/1912.07976/) (2019)
- [Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis](https://mlsanity.com/paper/1906.01213/) (2019)
- [Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification](https://mlsanity.com/paper/1906.04501/) (2019)
- [Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network](https://mlsanity.com/paper/2108.02352/) (2021)

## Built on by (most cited first, 3 of 3)

- [Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2201.04831/) (2022)
- [Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents](https://mlsanity.com/paper/2505.24331/) (2025)
- [Exploiting Contextual Target Attributes for Target Sentiment Classification](https://mlsanity.com/paper/2312.13766/) (2023)

## Abstract (arXiv)

Aspect level sentiment classification (ALSC) is a difficult problem with state-of-the-art models showing less than 80% macro-F1 score on benchmark datasets. Existing models do not incorporate information on aspect-aspect relations in knowledge graphs (KGs), e.g. DBpedia. Two main challenges stem from inaccurate disambiguation of aspects to KG entities, and the inability to learn aspect representations from the large KGs in joint training with ALSC models. We propose AR-BERT, a novel two-level global-local entity embedding scheme that allows efficient joint training of KG-based aspect embeddings and ALSC models. A novel incorrect disambiguation detection technique addresses the problem of inaccuracy in aspect disambiguation. We also introduce the problem of determining mode significance in multi-modal explanation generation, and propose a two step solution. The proposed methods show a consistent improvement of 2.5 - 4.1 percentage points, over the recent BERT-based baselines on benchmark datasets. The code is available at https://github.com/mainuliitkgp/AR-BERT.git.