arXiv:1809.01499
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Center-guided Classifier for Semantic Segmentation of Remote Sensing Images
Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing
TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision
Recurrent Alignment with Hard Attention for Hierarchical Text Rating
Mutual Distillation Learning For Person Re-Identification
Vamos: Versatile Action Models for Video Understanding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.