no code implementations • EMNLP 2021 • Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang
Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP).
no code implementations • 29 Nov 2021 • Xiaofei Sun, Jiwei Li, Xiaoya Li, Ziyao Wang, Tianwei Zhang, Han Qiu, Fei Wu, Chun Fan
In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples have greater impacts on each other during training.
2 code implementations • NAACL 2022 • Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Yi Yang, Shangwei Guo, Chun Fan
To deal with this issue, in this paper, we propose a new strategy to perform textual backdoor attacks which do not require an external trigger, and the poisoned samples are correctly labeled.
no code implementations • ICLR 2022 • Kangjie Chen, Yuxian Meng, Xiaofei Sun, Shangwei Guo, Tianwei Zhang, Jiwei Li, Chun Fan
The key feature of our attack is that the adversary does not need prior information about the downstream tasks when implanting the backdoor to the pre-trained model.
no code implementations • COLING 2022 • Xiaofei Sun, Yufei Tian, Yuxian Meng, Nanyun Peng, Fei Wu, Jiwei Li, Chun Fan
Then based on the paraphrase pairs produced by these UMT models, a unified surrogate model can be trained to serve as the final \sts model to generate paraphrases, which can be directly used for test in the unsupervised setup, or be finetuned on labeled datasets in the supervised setup.
no code implementations • EMNLP 2021 • Yuxian Meng, Xiang Ao, Qing He, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Fan, Jiwei Li
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals.
1 code implementation • 29 Aug 2021 • Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang
For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model.
no code implementations • EMNLP 2021 • Chun Fan, Jiwei Li, Xiang Ao, Fei Wu, Yuxian Meng, Xiaofei Sun
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level.
no code implementations • 30 May 2021 • Chun Fan, Yuxian Meng, Xiaofei Sun, Fei Wu, Tianwei Zhang, Jiwei Li
Next, based on this recurrent net that is able to generalize SEIR simulations, we are able to transform the objective to a differentiable one with respect to $\Theta_\text{SEIR}$, and straightforwardly obtain its optimal value.
no code implementations • 17 May 2021 • Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan
The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context.
2 code implementations • ACL 2022 • Leilei Gan, Yuxian Meng, Kun Kuang, Xiaofei Sun, Chun Fan, Fei Wu, Jiwei Li
The proposed method has the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans.
1 code implementation • 3 Dec 2020 • Zijun Sun, Chun Fan, Qinghong Han, Xiaofei Sun, Yuxian Meng, Fei Wu, Jiwei Li
The proposed model comes with the following merits: (1) span weights make the model self-explainable and do not require an additional probing model for interpretation; (2) the proposed model is general and can be adapted to any existing deep learning structures in NLP; (3) the weight associated with each text span provides direct importance scores for higher-level text units such as phrases and sentences.
1 code implementation • 17 Nov 2020 • Zijun Sun, Chun Fan, Xiaofei Sun, Yuxian Meng, Fei Wu, Jiwei Li
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining?
Ranked #1000000000 on Text Classification on IMDb
no code implementations • COLING 2022 • Xiaofei Sun, Zijun Sun, Yuxian Meng, Jiwei Li, Chun Fan
The difficulty of generating coherent long texts lies in the fact that existing models overwhelmingly focus on predicting local words, and cannot make high level plans on what to generate or capture the high-level discourse dependencies between chunks of texts.
no code implementations • 14 Oct 2020 • Yuxian Meng, Chun Fan, Zijun Sun, Eduard Hovy, Fei Wu, Jiwei Li
Any prediction from a model is made by a combination of learning history and test stimuli.