# Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts

arXiv: https://arxiv.org/abs/1809.01499 · HTML: https://mlsanity.com/paper/1809.01499/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2018.

## Built on by (most cited first, 9 of 9)

- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Understanding Interlocking Dynamics of Cooperative Rationalization](https://mlsanity.com/paper/2110.13880/) (2021)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making](https://mlsanity.com/paper/2205.05126/) (2022)
- [What to Learn, and How: Toward Effective Learning from Rationales](https://mlsanity.com/paper/2112.00071/) (2021)
- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [On Evaluating Explanation Utility for Human-AI Decision Making in NLP](https://mlsanity.com/paper/2407.03545/) (2024)
- [Rationalizing Predictions by Adversarial Information Calibration](https://mlsanity.com/paper/2301.06009/) (2023)
- [What's Mine becomes Yours: Defining, Annotating and Detecting Context-Dependent Paraphrases in News Interview Dialogs](https://mlsanity.com/paper/2404.06670/) (2024)

## Abstract (arXiv)

We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the important domain of detecting personal attacks in social media comments, we additionally demonstrate the importance of manually setting a semantically appropriate `default' behavior for the model by explicitly manipulating its bias term. We develop a validation set of human-annotated personal attacks to evaluate the impact of these changes.