| HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task | Nov 1, 2021 | AllData Augmentation | —Unverified | 0 |
| Bounds all around: training energy-based models with bidirectional bounds | Nov 1, 2021 | AllDensity Estimation | —Unverified | 0 |
| How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding | Nov 1, 2021 | Adversarial RobustnessAll | —Unverified | 0 |
| Don’t Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques | Nov 1, 2021 | AllBias Detection | CodeCode Available | 0 |
| Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations | Nov 1, 2021 | All | —Unverified | 0 |
| AMuSE-WSD: An All-in-one Multilingual System for Easy Word Sense Disambiguation | Nov 1, 2021 | AllWord Sense Disambiguation | —Unverified | 0 |
| All-In-One: Artificial Association Neural Networks | Oct 31, 2021 | All | —Unverified | 0 |
| Backdoor Pre-trained Models Can Transfer to All | Oct 30, 2021 | AllBackdoor Attack | CodeCode Available | 0 |
| One model to enhance them all: array geometry agnostic multi-channel personalized speech enhancement | Oct 20, 2021 | AllAutomatic Speech Recognition | —Unverified | 0 |
| One Instrument to Rule Them All: The Bias and Coverage of Just-ID IV | Oct 20, 2021 | All | —Unverified | 0 |
