Vaidehi Patil

Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages

2022 · arXiv (Cornell University)

Pre-trained multilingual language models such as mBERT and XLM-R have demonstrated great potential for zero-shot cross-lingual transfer to low web-resource languages (LRL). However, due to limited model capacity, the large difference in the sizes of …

Debiasing Multimodal Models via Causal Information Minimization

2023 · arXiv (Cornell University)

Most existing debiasing methods for multimodal models, including causal intervention and inference methods, utilize approximate heuristics to represent the biases, such as shallow features from early stages of training or unimodal features for multimodal tasks …