1 code implementation • 24 Oct 2022 • Changlong Yu, Tianyi Xiao, Lingpeng Kong, Yangqiu Song, Wilfred Ng
Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate human-defined linguistic priors into task-specific fine-tuning.
1 code implementation • ACL 2022 • Jun Gao, Wei Wang, Changlong Yu, Huan Zhao, Wilfred Ng, Ruifeng Xu
Representations of events described in text are important for various tasks.
1 code implementation • Findings (ACL) 2022 • Changlong Yu, Hongming Zhang, Yangqiu Song, Wilfred Ng
Large-scale pre-trained language models have demonstrated strong knowledge representation ability.
1 code implementation • 24 Oct 2020 • Fuyu Lv, Mengxue Li, Tonglei Guo, Changlong Yu, Fei Sun, Taiwei Jin, Wilfred Ng
The offline experimental results based on real-world E-commerce data demonstrate the effectiveness and verify the importance of unclicked items in sequential recommendation.
1 code implementation • EMNLP 2020 • Changlong Yu, Jialong Han, Peifeng Wang, Yangqiu Song, Hongming Zhang, Wilfred Ng, Shuming Shi
We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases.
no code implementations • ACL 2020 • Changlong Yu, Jialong Han, Haisong Zhang, Wilfred Ng
Hypernymy detection, a. k. a, lexical entailment, is a fundamental sub-task of many natural language understanding tasks.
1 code implementation • AKBC 2020 • Changlong Yu, Hongming Zhang, Yangqiu Song, Wilfred Ng, Lifeng Shang
Computational and cognitive studies suggest that the abstraction of eventualities (activities, states, and events) is crucial for humans to understand daily eventualities.
1 code implementation • IJCNLP 2019 • Hongming Zhang, Jiaxin Bai, Yan Song, Kun Xu, Changlong Yu, Yangqiu Song, Wilfred Ng, Dong Yu
Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words.
2 code implementations • 1 Sep 2019 • Fuyu Lv, Taiwei Jin, Changlong Yu, Fei Sun, Quan Lin, Keping Yang, Wilfred Ng
In this paper, we propose a new sequential deep matching (SDM) model to capture users' dynamic preferences by combining short-term sessions and long-term behaviors.