9 citations · 10 across the 3 of their papers we have counts for
5 papers
Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model
Qiao Cheng, Jin Huang, Yitao Duan
This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is b…
Octopus: Privacy-Preserving Collaborative Evaluation of Loan Stacking
Yi Li, Kevin Gao, Yitao Duan +1
With the rise of online lenders, the loan stacking problem has become a significant issue in the financial industry. One of the key steps in the fight against it is the querying of…
Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training
Qiao Cheng, Meiyuan Fang, Yaqian Han +2
In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard…
No Place to Hide: Catching Fraudulent Entities in Tensors
Yikun Ban, Xin Liu, Yitao Duan +2
Many approaches focus on detecting dense blocks in the tensor of multimodal data to prevent fraudulent entities (e.g., accounts, links) from retweet boosting, hashtag hijacking, li…
BadLink: Combining Graph and Information-Theoretical Features for Online Fraud Group Detection
Yikun Ban, Xin Liu, Tianyi Zhang +4
Frauds severely hurt many kinds of Internet businesses. Group-based fraud detection is a popular methodology to catch fraudsters who unavoidably exhibit synchronized behaviors. We…