forked from academicpages/academicpages.github.io
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
9 additions
and
9 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,15 +1,15 @@ | ||
| --- | ||
| title: "Paper Title Number 1" | ||
| title: "Robust Hate Speech Detection via Mitigating Spurious Correlations" | ||
| collection: publications | ||
| permalink: /publication/2009-10-01-paper-title-number-1 | ||
| excerpt: 'This paper is about the number 1. The number 2 is left for future work.' | ||
| date: 2009-10-01 | ||
| permalink: /publication/robust-hate-speech-detection | ||
| excerpt: 'This paper is about removing the causal connection of spurious correlated words to develop a robust hate speech detection model.' | ||
| date: 2022-10-01 | ||
| venue: 'Journal 1' | ||
| paperurl: 'http://academicpages.github.io/files/paper1.pdf' | ||
| citation: 'Your Name, You. (2009). "Paper Title Number 1." <i>Journal 1</i>. 1(1).' | ||
| paperurl: 'https://aclanthology.org/2022.aacl-short.7' | ||
| citation: [Robust Hate Speech Detection via Mitigating Spurious Correlations](https://aclanthology.org/2022.aacl-short.7) (Tiwari et al., AACL-IJCNLP 2022) | ||
| --- | ||
| This paper is about the number 1. The number 2 is left for future work. | ||
| We develop a novel robust hate speech detection model that can defend against both wordand character-level adversarial attacks. We identify the essential factor that vanilla detection models are vulnerable to adversarial attacks is the spurious correlation between certain target words in the text and the prediction label. To mitigate such spurious correlation, we describe the process of hate speech detection by a causal graph. Then, we employ the causal strength to quantify the spurious correlation and formulate a regularized entropy loss function. We show that our method generalizes the backdoor adjustment technique in causal inference. | ||
|
|
||
| [Download paper here](http://academicpages.github.io/files/paper1.pdf) | ||
| [Read Paper Here](https://aclanthology.org/2022.aacl-short.7.pdf) | ||
|
|
||
| Recommended citation: Your Name, You. (2009). "Paper Title Number 1." <i>Journal 1</i>. 1(1). | ||
| Recommended citation: [Robust Hate Speech Detection via Mitigating Spurious Correlations](https://aclanthology.org/2022.aacl-short.7) (Tiwari et al., AACL-IJCNLP 2022) |