1 code implementation • 4 Jul 2024 • Yongjie Wang, Xiaoqi Qiu, Yu Yue, Xu Guo, Zhiwei Zeng, Yuhong Feng, Zhiqi Shen
Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class.
1 code implementation • 9 Jun 2024 • Xiaoqi Qiu, Yongjie Wang, Xu Guo, Zhiwei Zeng, Yue Yu, Yuhong Feng, Chunyan Miao
Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes.
no code implementations • 15 Mar 2024 • Yongjie Wang, Tong Zhang, Xu Guo, Zhiqi Shen
Due to the lack of a rigorous definition of explainable AI (XAI), a plethora of research related to explainability, interpretability, and transparency has been developed to explain and analyze the model from various perspectives.
1 code implementation • 9 Sep 2023 • Yongjie Wang, Hangwei Qian, Yongjie Liu, Wei Guo, Chunyan Miao
Existing methods fail to exploit flexibility and address the concerns of non-robustness simultaneously.
no code implementations • 3 May 2023 • Ruochen Zhao, Shafiq Joty, Yongjie Wang, Tan Wang
The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions.
no code implementations • 13 May 2022 • Yongjie Wang, Hangwei Qian, Chunyan Miao
We then propose DualCF strategy to circumvent the above issues, which is achieved by taking not only CF but also counterfactual explanation of CF (CCF) as pairs of training samples for the substitute model.
1 code implementation • NAACL 2022 • Yongjie Wang, Chuan Wang, Ruobing Li, Hui Lin
In recent years, pre-trained models have become dominant in most natural language processing (NLP) tasks.
Ranked #2 on
Automated Essay Scoring
on ASAP-AES
no code implementations • 23 Apr 2019 • Ankush Agarwal, Christian-Oliver Ewald, Yongjie Wang
We transform this constrained optimal investment problem into an unconstrained problem by replicating a self-financing portfolio of future contributions from the member and the minimum guarantee provided by the scheme.
no code implementations • 23 Jan 2019 • Jonathan Schwartz, Yi Jiang, Yongjie Wang, Anthony Aiello, Pallab Bhattacharya, Hui Yuan, Zetian Mi, Nabil Bassim, Robert Hovden
Highly-directional image artifacts such as ion mill curtaining, mechanical scratches, or image striping from beam instability degrade the interpretability of micrographs.
no code implementations • 5 Oct 2018 • Yong Luo, Huaizheng Zhang, Yongjie Wang, Yonggang We, Xinwen Zhang
We compare the different variants with our baseline model.