no code implementations • 6 Jan 2024 • Shaobo Cui, Lazar Milikic, Yiyang Feng, Mete Ismayilzada, Debjit Paul, Antoine Bosselut, Boi Faltings
CESAR achieves a significant 69. 7% relative improvement over existing metrics, increasing from 47. 2% to 80. 1% in capturing the causal strength change brought by supporters and defeaters.
no code implementations • 18 Apr 2023 • Haolan Zhan, Xuming Lin, Shaobo Cui, Zhongzhou Zhao, Wei Zhou, Haiqing Chen
Specifically, tabular data and persona information are firstly represented as latent variables separately.
no code implementations • 18 Aug 2021 • Xuming Lin, Shaobo Cui, Zhongzhou Zhao, Wei Zhou, Ji Zhang, Haiqing Chen
With these two synergic representations, we then regroup these phrases into a fine-grained plan, based on which we generate the final long text.
no code implementations • 17 Aug 2021 • Shaobo Cui, Xintong Bao, Xuming Lin, Zhongzhou Zhao, Ji Zhang, Wei Zhou, Haiqing Chen
Each one-to-one mapping is associated with a conditional generation pattern and is modeled with an expert in SPMoE.
no code implementations • 24 Feb 2021 • Shaobo Cui, Xintong Bao, Xinxing Zu, Yangyang Guo, Zhongzhou Zhao, Ji Zhang, Haiqing Chen
This pipeline approach, however, is undesired in mining the most appropriate QA pairs from documents since it ignores the connection between question generation and answer extraction, which may lead to incompatible QA pair generation, i. e., the selected answer span is inappropriate for question generation.
no code implementations • 27 May 2020 • Zehao Lin, Shaobo Cui, Guodun Li, Xiaoming Kang, Feng Ji, FengLin Li, Zhongzhou Zhao, Haiqing Chen, Yin Zhang
More specifically, we take advantage of a decision model to help the dialogue system decide whether to wait or answer.
no code implementations • 21 May 2020 • Shuke Peng, Feng Ji, Zehao Lin, Shaobo Cui, Haiqing Chen, Yin Zhang
How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response.
no code implementations • 22 Feb 2020 • Zehao Lin, Shaobo Cui, Guodun Li, Xiaoming Kang, Feng Ji, FengLin Li, Zhongzhou Zhao, Haiqing Chen, Yin Zhang
And the arbitrator decides whether to wait or to make a response to the user directly.
no code implementations • WS 2019 • Shaobo Cui, Rongzhong Lian, Di Jiang, Yuanfeng Song, Siqi Bao, Yong Jiang
DAL is the first work to innovatively utilizes the duality between query generation and response generation to avoid safe responses and increase the diversity of the generated responses.