# XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision

arXiv: https://arxiv.org/abs/2311.00189 · HTML: https://mlsanity.com/paper/2311.00189/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [Weakly-Supervised Neural Text Classification](https://mlsanity.com/paper/1809.01478/) (2018)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)
- [Towards better understanding of gradient-based attribution methods for Deep Neural Networks](https://mlsanity.com/paper/1711.06104/) (2017)
- [X-Class: Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2010.12794/) (2020)
- [Weakly-supervised Text Classification Based on Keyword Graph](https://mlsanity.com/paper/2110.02591/) (2021)
- [Learning with Weak Supervision for Email Intent Detection](https://mlsanity.com/paper/2005.13084/) (2020)
- [Weakly Supervised Text Classification using Supervision Signals from a Language Model](https://mlsanity.com/paper/2205.06604/) (2022)
- [Unsupervised Key Event Detection from Massive Text Corpora](https://mlsanity.com/paper/2206.04153/) (2022)

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

- [Distilling Large Language Models for Text-Attributed Graph Learning](https://mlsanity.com/paper/2402.12022/) (2024)
- [DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation](https://mlsanity.com/paper/2403.10831/) (2024)
- [MEGL: Multimodal Explanation-Guided Learning](https://mlsanity.com/paper/2411.13053/) (2024)

## Abstract (arXiv)

Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and labor-intensive. To address this issue, recent studies have focused on weakly-supervised and extremely weakly-supervised settings, which require minimal or no human annotation, respectively. In previous methods of weakly supervised text classification, pseudo-training data is generated by assigning pseudo-labels to documents based on their alignment (e.g., keyword matching) with specific classes. However, these methods ignore the importance of incorporating the explanations of the generated pseudo-labels, or saliency of individual words, as additional guidance during the text classification training process. To address this limitation, we propose XAI-CLASS, a novel explanation-enhanced extremely weakly-supervised text classification method that incorporates word saliency prediction as an auxiliary task. XAI-CLASS begins by employing a multi-round question-answering process to generate pseudo-training data that promotes the mutual enhancement of class labels and corresponding explanation word generation. This pseudo-training data is then used to train a multi-task framework that simultaneously learns both text classification and word saliency prediction. Extensive experiments on several weakly-supervised text classification datasets show that XAI-CLASS outperforms other weakly-supervised text classification methods significantly. Moreover, experiments demonstrate that XAI-CLASS enhances both model performance and explainability.