# Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations

arXiv: https://arxiv.org/abs/2302.10479 · HTML: https://mlsanity.com/paper/2302.10479/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 21 Feb 2023.

## Builds on (most cited first, 22 of 22)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models](https://mlsanity.com/paper/1909.09251/) (2019)
- [Automatic Text Scoring Using Neural Networks](https://mlsanity.com/paper/1606.04289/) (2016)
- [Attentional Encoder Network for Targeted Sentiment Classification](https://mlsanity.com/paper/1902.09314/) (2019)
- [Gradient-based Analysis of NLP Models is Manipulable](https://mlsanity.com/paper/2010.05419/) (2020)
- [Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers](https://mlsanity.com/paper/2010.00667/) (2020)
- [Detecting Linguistic Characteristics of Alzheimer's Dementia by Interpreting Neural Models](https://mlsanity.com/paper/1804.06440/) (2018)
- [Interpreting Neural Networks to Improve Politeness Comprehension](https://mlsanity.com/paper/1610.02683/) (2016)
- [Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens](https://mlsanity.com/paper/1805.02214/) (2018)

## Built on by (most cited first, 2 of 2)

- [Metacognition-Enhanced Few-Shot Prompting With Positive Reinforcement](https://mlsanity.com/paper/2312.08642/) (2023)
- [Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2402.18145/) (2024)

## Abstract (arXiv)

Gradient-based explanation methods play an important role in the field of interpreting complex deep neural networks for NLP models. However, the existing work has shown that the gradients of a model are unstable and easily manipulable, which impacts the model's reliability largely. According to our preliminary analyses, we also find the interpretability of gradient-based methods is limited for complex tasks, such as aspect-based sentiment classification (ABSC). In this paper, we propose an Interpretation-Enhanced Gradient-based framework for ABSC via a small number of explanation annotations, namely textttIEGA. Particularly, we first calculate the word-level saliency map based on gradients to measure the importance of the words in the sentence towards the given aspect. Then, we design a gradient correction module to enhance the model's attention on the correct parts (e.g., opinion words). Our model is model agnostic and task agnostic so that it can be integrated into the existing ABSC methods or other tasks. Comprehensive experimental results on four benchmark datasets show that our textttIEGA can improve not only the interpretability of the model but also the performance and robustness.