Papers by Shijing Wang
Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Video dubbing systems use neural machine translation and text-to-speech technologies to translate original speech into visual media programs. |
| Approach: | They propose a preference optimization method to optimize video dubbing duration alignment . they propose combining segment-wise sampling and fine-grained loss to mitigate duration mismatches . |
| Outcome: | The proposed method achieves superior performance in duration alignment tasks. |
Methods for Numeracy-Preserving Word Embeddings (2020.emnlp-main)
Copied to clipboard
Dhanasekar Sundararaman, Shijing Si, Vivek Subramanian, Guoyin Wang, Devamanyu Hazarika, Lawrence Carin
| Challenge: | Word embedding models capture semantic relationships between words but fail to capture numerical properties associated with numbers. |
| Approach: | They propose a method to assign and learn embeddings for numbers using word embedders. |
| Outcome: | The proposed model outperforms pre-trained word embedding models across multiple examples of two tasks. |
Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pretrained language models are agnostic to downstream information and can overfit when fine-tuned with low resource datasets. |
| Approach: | They integrate label information as a task-specific prior into the self-attention component of pretrained BERT models. |
| Outcome: | Experiments on benchmarks and real-word datasets show that the proposed approach can improve the performance of pretrained models when fine-tuned with small datasets. |