Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks ( Findings of EMNLP 2021)

We propose a novel paradigm based on attention augmentation to introduce crucial cross-domain knowledge via a translation system. The proposed paradigm enables the model attention to draw cross-domain knowledge indicated by the implicit word-level cross-lingual alignment between the input and its corresponding translation. Aside from the model requiring crosslingual input, we also establish an off-the-shelf model which eludes the dependency on crosslingual translations. Experiments demonstrate that our proposal significantly advances the state-of-the-art results of cross-domain Chinese segmenting and labeling tasks.

The paper (Findings of EMNLP 2021) and code repo have been released.

Alt text


Feature Space Singularity for Out-of-Distribution Detection

We propose a simple yet effective algorithm named FSSD based on a novel observation: in a trained neural network, OoD samples with bounded norms well concentrate in the feature space. It achieves state-of-the-art performance on various OoD detection benchmark and enjoys robustness to slight corruption in test data.

Alt text

The paper (Safe AI workshop at AAAI 2021) and code repo have been released.