19 citations · 38 across the 10 of their papers we have counts for
13 papers
Extracted BERT Model Leaks More Information than You Think!
Xuanli He, Chen Chen, Lingjuan Lyu +1
The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing…
Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?
Thuy-Trang Vu, Shahram Khadivi, Xuanli He +2
Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). This paper investigates whether the domain information can be transf…
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks
Xuanli He, Qiongkai Xu, Yi Zeng +4
Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, a recent…
Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning
Xuanli He, Iman Keivanloo, Yi Xu +4
Pre-training and then fine-tuning large language models is commonly used to achieve state-of-the-art performance in natural language processing (NLP) tasks. However, most pre-train…
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection
Thuy-Trang Vu, Xuanli He, Dinh Phung +1
This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or ta…
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
Xuanli He, Lingjuan Lyu, Qiongkai Xu +1
Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows…