1 code implementation • 6 Jun 2023 • Shiguang Wu, Yaqing Wang, Qinghe Jing, daxiang dong, Dejing Dou, Quanming Yao
Instead of using a fixed modulation function and deciding modulation position by expertise, we propose a modulation framework called ColdNAS for user cold-start problem, where we look for proper modulation structure, including function and position, via neural architecture search.
1 code implementation • 14 Jul 2022 • Ji Liu, daxiang dong, Xi Wang, An Qin, Xingjian Li, Patrick Valduriez, Dejing Dou, dianhai yu
Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which exceed the capacity of small devices for inference and incurs long training time.
1 code implementation • 3 Jun 2021 • Hao liu, Qian Gao, Jiang Li, Xiaochao Liao, Hao Xiong, Guangxing Chen, Wenlin Wang, Guobao Yang, Zhiwei Zha, daxiang dong, Dejing Dou, Haoyi Xiong
In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.
1 code implementation • NAACL 2021 • Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, daxiang dong, Hua Wu, Haifeng Wang
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers.
Ranked #4 on Passage Retrieval on Natural Questions
no code implementations • 4 Dec 2019 • Liang Zhao, Yang Wang, daxiang dong, Hao Tian
The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage.
2 code implementations • ACL 2018 • Xiangyang Zhou, Lu Li, daxiang dong, Yi Liu, Ying Chen, Wayne Xin Zhao, dianhai yu, Hua Wu
Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context.
Ranked #6 on Conversational Response Selection on RRS
1 code implementation • ICLR 2018 • chao qiao, Bo Huang, guocheng niu, daren li, daxiang dong, wei he, dianhai yu, Hua Wu
In this paper, we propose a new method of learning and utilizing task-specific distributed representations of n-grams, referred to as “region embeddings”.