1 code implementation • 16 Jul 2023 • Zifeng Cheng, Qingyu Zhou, Zhiwei Jiang, Xuemin Zhao, Yunbo Cao, Qing Gu
However, these methods are only trained at a single granularity (i. e., either token level or span level) and have some weaknesses of the corresponding granularity.
1 code implementation • 1 Mar 2023 • Cong Wang, Zhiwei Jiang, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu
For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes.
1 code implementation • 16 Apr 2022 • Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Qing Gu
In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model's overconfident on known intents.
1 code implementation • COLING 2020 • Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Hua Yu, Qing Gu
Each subnetwork is composed of a clause representation learner and a local pair searcher.