# Rationale-Augmented Convolutional Neural Networks for Text Classification

arXiv: https://arxiv.org/abs/1605.04469 · HTML: https://mlsanity.com/paper/1605.04469/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2016.

## Built on by (most cited first, 30 of 39)

- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step](https://mlsanity.com/paper/2306.14050/) (2023)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://mlsanity.com/paper/2103.13084/) (2021)
- [When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data](https://mlsanity.com/paper/2102.02201/) (2021)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation](https://mlsanity.com/paper/2402.04616/) (2024)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Explain and Predict, and then Predict Again](https://mlsanity.com/paper/2101.04109/) (2021)
- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [What to Learn, and How: Toward Effective Learning from Rationales](https://mlsanity.com/paper/2112.00071/) (2021)
- [Rissanen Data Analysis: Examining Dataset Characteristics via Description Length](https://mlsanity.com/paper/2103.03872/) (2021)
- [Rationalization for Explainable NLP: A Survey](https://mlsanity.com/paper/2301.08912/) (2023)
- [A survey on improving NLP models with human explanations](https://mlsanity.com/paper/2204.08892/) (2022)
- [Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction](https://mlsanity.com/paper/2112.10424/) (2021)
- [ToxCCIn: Toxic Content Classification with Interpretability](https://mlsanity.com/paper/2103.01328/) (2021)
- [An Information Retrieval Approach to Building Datasets for Hate Speech Detection](https://mlsanity.com/paper/2106.09775/) (2021)
- [Human-Centric Research for NLP: Towards a Definition and Guiding Questions](https://mlsanity.com/paper/2207.04447/) (2022)
- [Diagnostics-Guided Explanation Generation](https://mlsanity.com/paper/2109.03756/) (2021)
- [Practical Benefits of Feature Feedback Under Distribution Shift](https://mlsanity.com/paper/2110.07566/) (2021)
- [Improving the trustworthiness of image classification models by utilizing bounding-box annotations](https://mlsanity.com/paper/2108.10131/) (2021)
- [REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization](https://mlsanity.com/paper/2310.14418/) (2023)
- [Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning](https://mlsanity.com/paper/2311.07099/) (2023)
- [Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark](https://mlsanity.com/paper/2411.18831/) (2024)
- [PALRACE: Reading Comprehension Dataset with Human Data and Labeled Rationales](https://mlsanity.com/paper/2106.12373/) (2021)
- [Image Classification with Consistent Supporting Evidence](https://mlsanity.com/paper/2111.07048/) (2021)
- [Supervised Attention in Sequence-to-Sequence Models for Speech Recognition](https://mlsanity.com/paper/2204.12308/) (2022)
- [Making Document-Level Information Extraction Right for the Right Reasons](https://mlsanity.com/paper/2110.07686/) (2021)

## Abstract (arXiv)

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or snippets) that support their overall document categorization, i.e., they provide rationales. Our model exploits such supervision via a hierarchical approach in which each document is represented by a linear combination of the vector representations of its component sentences. We propose a sentence-level convolutional model that estimates the probability that a given sentence is a rationale, and we then scale the contribution of each sentence to the aggregate document representation in proportion to these estimates. Experiments on five classification datasets that have document labels and associated rationales demonstrate that our approach consistently outperforms strong baselines. Moreover, our model naturally provides explanations for its predictions.