no code implementations • CCL 2022 • Yang Zhao, Zhang Yuanzhe, Jiang Zhongtao, Ju Yiming, Zhao Jun, Liu Kang
“Explanations can increase the transparency of neural networks and make them more trustworthy.
no code implementations • CCL 2021 • Liu Zhuang, Lin Wayne, Shi Ya, Zhao Jun
“In the paper we present a ‘pre-training’+‘post-training’+‘fine-tuning’ three-stage paradigm which is a supplementary framework for the standard ‘pre-training’+‘fine-tuning’ languagemodel approach.
no code implementations • CCL 2022 • Zhao Jun, Hu Yuan, Xu Nuo, Gui Tao, Zhang Qi, Chen Yunwen, Gao Xiang
In addition, very few relation descriptions are exposed to the model during training, which we argue is the performance bottleneck of two-tower methods.
no code implementations • CCL 2022 • Zhao Jun, Zhang Yongxin, Xu Nuo, Gui Tao, Zhang Qi, Chen Yunwen, Gao Xiang
“Supervised learning is a classic paradigm of relation extraction (RE).
no code implementations • CCL 2021 • Tian Zhixing, Zhang Yuanzhe, Liu Kang, Zhao Jun
Having realized this we propose a novel method that utilizes the topic knowledge implied by the clustered messages to aid in the comprehension of those short messages.
no code implementations • CCL 2021 • Yu Xiaoyan, Liu Qingbin, He Shizhu, Liu Kang, Liu Shengping, Zhao Jun, Zhou Yongbin
“The irrelevant information in documents poses a great challenge for machine reading compre-hension (MRC).
no code implementations • 5 Oct 2020 • Xu Huaqiang, Zhang Guodong, Zhao Jun, Quoc-Viet Pham
Intelligent Reflecting Surface (IRS) is envisioned to be a promising green and cost-effective solution to enhance wireless network performance by smartly reconfiguring the signal propagation.
Networking and Internet Architecture
no code implementations • 19 Jun 2018 • Brenner Eliot, Zhao Jun, Kutiyanawala Aliasgar, Yan Zheng
The different types of relevance models developed for IR have complementary advantages and disadvantages when applied to eCommerce product search.
no code implementations • 18 Aug 2015 • Hao Zongbo, Lu Linlin, Zhang Qianni, Wu Jie, Izquierdo Ebroul, Yang Juanyu, Zhao Jun
In the subdivision stage of the proposed SFM, samples in each category are clustered.