no code implementations • ACL 2022 • Juncheng Wan, Dongyu Ru, Weinan Zhang, Yong Yu
In this work, we try to improve the span representation by utilizing retrieval-based span-level graphs, connecting spans and entities in the training data based on n-gram features.
no code implementations • 14 Aug 2022 • Wenyan Liu, Juncheng Wan, Xiaoling Wang, Weinan Zhang, Dell Zhang, Hang Li
In this paper, we investigate fast machine unlearning techniques for recommender systems that can remove the effect of a small amount of training data from the recommendation model without incurring the full cost of retraining.
no code implementations • COLING 2022 • Juncheng Wan, Jian Yang, Shuming Ma, Dongdong Zhang, Weinan Zhang, Yong Yu, Zhoujun Li
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable.
no code implementations • NAACL 2021 • Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, Ming Zhou
Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left.
1 code implementation • 25 May 2019 • Yaoming Zhu, Juncheng Wan, Zhiming Zhou, Liheng Chen, Lin Qiu, Wei-Nan Zhang, Xin Jiang, Yong Yu
Knowledge base is one of the main forms to represent information in a structured way.