Papers by Linzhi Wu
Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)
Copied to clipboard
| Challenge: | Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability . |
| Approach: | They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features. |
| Outcome: | Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios. |
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting (2022.naacl-main)
Copied to clipboard
| Challenge: | Prior research has focused on reducing noise for specific methods to achieve an effective integration. |
| Approach: | They propose to use token substitution and mixup to improve named entity recognition (NER) using a meta-reweighting strategy, which is extensible and requires little effort. |
| Outcome: | The proposed method is extensible, imposing little effort on a specific self-augmentation method. |
Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent research on slot filling has witnessed considerable improvement with considerable data and label shifts. |
| Approach: | They propose an adaptive end-to-end metric learning scheme for zero-shot slot filling that uses context-aware soft label representations and slot-level contrastive representation learning to mitigate the data and label shift problems. |
| Outcome: | The proposed approach outperforms existing methods on public benchmarks and shows that it is simple, efficient and generalizable. |