1 code implementation • 18 Feb 2024 • Yichen Wang, Shangbin Feng, Abe Bohan Hou, Xiao Pu, Chao Shen, Xiaoming Liu, Yulia Tsvetkov, Tianxing He
Our experiments reveal that almost none of the existing detectors remain robust under all the attacks, and all detectors exhibit different loopholes.
no code implementations • 2 Feb 2024 • Mingqi Gao, Xinyu Hu, Jie Ruan, Xiao Pu, Xiaojun Wan
Evaluating natural language generation (NLG) is a vital but challenging problem in artificial intelligence.
no code implementations • 8 Oct 2023 • Xiao Pu, Jingyu Zhang, Xiaochuang Han, Yulia Tsvetkov, Tianxing He
The rampant proliferation of large language models, fluent enough to generate text indistinguishable from human-written language, gives unprecedented importance to the detection of machine-generated text.
no code implementations • 18 Sep 2023 • Xiao Pu, Mingqi Gao, Xiaojun Wan
How well can large language models (LLMs) generate summaries?
no code implementations • 18 Jul 2023 • Lin Yuan, Kai Liang, Xiao Pu, Yan Zhang, Jiaxu Leng, Tao Wu, Nannan Wang, Xinbo Gao
This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.
no code implementations • 24 May 2023 • Xiao Pu, Mingqi Gao, Xiaojun Wan
The results show that summaries generated by fine-tuned models lead to higher consistency in usefulness across all three tasks, as rankings of fine-tuned summarization systems are close across downstream tasks according to the proposed extrinsic metrics.
1 code implementation • 28 Oct 2022 • Yan Zhang, Xiyuan Gao, Qingyan Duan, Jiaxu Leng, Xiao Pu, Xinbo Gao
By stacking various layers of CSA blocks, we propose the Fourier Complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners.
1 code implementation • TACL 2018 • Xiao Pu, Nikolaos Pappas, James Henderson, Andrei Popescu-Belis
We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones.
no code implementations • EACL 2017 • Xiao Pu, Laura Mascarell, Andrei Popescu-Belis
We compare the automatic post-editing of noun translations with the re-ranking of the translation hypotheses based on the classifiers{'} output, and also use these methods in combination.
1 code implementation • 23 Feb 2016 • Ery Arias-Castro, Xiao Pu
Consider the problem of sparse clustering, where it is assumed that only a subset of the features are useful for clustering purposes.