Skip to content
conftrace_

attention augmentation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

continual knowledge learning (1) token importance (1) topic segmentation (1) bert-based model (1) attention pattern (1) large language model (1) neural network (1) interpretable attention pattern (1) cross-domain adaptation (1) multi-head self-attention (1)

Papers

Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning NeurIPS 2024 Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation EMNLP 2022 Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks EMNLP 2021