no code implementations • Findings (ACL) 2022 • Yao Zhao, Jiacheng Huang, Wei Hu, Qijin Chen, Xiaoxia Qiu, Chengfu Huo, Weijun Ren
In this paper, we propose an implicit RL method called ImRL, which links relation phrases in NL to relation paths in KG.
no code implementations • 5 Mar 2024 • Wei Bao, Mi Zhang, Tao Zhang, Chengfu Huo
Query Auto-Completion(QAC), as an important part of the modern search engine, plays a key role in complementing user queries and helping them refine their search intentions. Today's QAC systems in real-world scenarios face two major challenges:1)intention equivocality(IE): during the user's typing process, the prefix often contains a combination of characters and subwords, which makes the current intention ambiguous and difficult to model. 2)intention transfer (IT):previous works make personalized recommendations based on users' historical sequences, but ignore the search intention transfer. However, the current intention extracted from prefix may be contrary to the historical preferences.
no code implementations • 25 Jul 2023 • Zhao-Yang Liu, Liucheng Sun, Chenwei Weng, Qijin Chen, Chengfu Huo
In this paper, we propose a novel Gaussian Graph with Prototypical Contrastive Learning (GPCL) framework to overcome these challenges.
1 code implementation • 21 Jan 2022 • Jiacheng Huang, Yao Zhao, Wei Hu, Zhen Ning, Qijin Chen, Xiaoxia Qiu, Chengfu Huo, Weijun Ren
In this paper, we propose a new trustworthy method that exploits facts for a KG based on multi-sourced noisy data and existing facts in the KG.
no code implementations • 11 Mar 2021 • Bang Lin, Xiuchong Wang, Yu Dong, Chengfu Huo, Weijun Ren, Chuanyu Xu
Specially, MHN employs node base embedding to encapsulate node attributes, BFS and DFS neighbors aggregation within a metapath to capture local and global information, and metapaths aggregation to combine different semantics of the heterogeneous graph.
no code implementations • 14 Jan 2021 • Ben Chen, Bin Chen, Dehong Gao, Qijin Chen, Chengfu Huo, Xiaonan Meng, Weijun Ren, Yang Zhou
However, universal language models may perform weakly in these fake news detection for lack of large-scale annotated data and sufficient semantic understanding of domain-specific knowledge.
no code implementations • 23 Aug 2020 • Liangwei Li, Liucheng Sun, Chenwei Weng, Chengfu Huo, Weijun Ren
We call this problem the coupon allocation problem.
2 code implementations • Proceedings of the AAAI Conference on Artificial Intelligence 2020 • Ze Lye, Yu Dong, Chengfu Huo, Weijun Ren
In User-to-Item Network, we represent the relevance between user and item by inner product of the corresponding representation in the embedding space.