Jiahao Xu

SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives

2023 · arXiv (Cornell University)

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative pairs affects the model's …

Decoding sentiment: A sentiment analysis model for movie reviews

2024 · Applied and Computational Engineering

Sentiment analysis of movie reviews can provide valuable insights into movie reactions and preferences. To this end, this study proposes the Convolutional Long Short-Term Memory (ConvLSTM) neural network for movie review sentiment analysis. ConvLSTM can …

Findings of the WMT 2024 Shared Task on Discourse-Level Literary Translation

2024

Longyue Wang, Siyou Liu, Chenyang Lyu, Wenxiang Jiao, Xing Wang, Jiahao Xu, Zhaopeng Tu, Yan Gu, Weiyu Chen, Minghao Wu, Liting Zhou, Philipp Koehn, Andy Way, Yulin Yuan. Proceedings of the Ninth Conference on Machine …

Traceable Black-box Watermarks for Federated Learning

2025 · arXiv (Cornell University)

Due to the distributed nature of Federated Learning (FL) systems, each local client has access to the global model, which poses a critical risk of model leakage. Existing works have explored injecting watermarks into local …