no code implementations • SemEval (NAACL) 2022 • Ye Wang, Yanmeng Wang, Baishun Ling, Zexiang Liao, Shaojun Wang, Jing Xiao
This paper describes the second-placed system for subtask 2 and the ninth-placed system for subtask 1 in SemEval 2022 Task 4: Patronizing and Condescending Language Detection.
no code implementations • 6 Feb 2023 • Zhiwei Tang, Yanmeng Wang, Tsung-Hui Chang
In this paper, we propose a novel noisy perturbation scheme with a general symmetric noise distribution for sign-based compression, which not only allows one to flexibly control the tradeoff between gradient bias and convergence performance, but also provides a unified viewpoint to existing stochastic sign-based methods.
1 code implementation • 8 Jan 2023 • Yanmeng Wang, Qingjiang Shi, Tsung-Hui Chang
In view of this, we develop a new FL algorithm that is tailored to BN, called FedTAN, which is capable of achieving robust FL performance under a variety of data distributions via iterative layer-wise parameter aggregation.
1 code implementation • 1 Nov 2022 • Jianfei Zhang, Jun Bai, Chenghua Lin, Yanmeng Wang, Wenge Rong
There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and hole problem, i. e., mismatch between the aggregated posterior distribution and the prior distribution.
no code implementations • Findings (EMNLP) 2021 • Yanmeng Wang, Jun Bai, Ye Wang, Jianfei Zhang, Wenge Rong, Zongcheng Ji, Shaojun Wang, Jing Xiao
To keep independent encoding of questions and answers during inference stage, variational auto-encoder is further introduced to reconstruct answers (questions) from question (answer) embeddings as an auxiliary task to enhance QA interaction in representation learning in training stage.
no code implementations • SEMEVAL 2021 • Ye Wang, Yanmeng Wang, Haijun Zhu, Bo Zeng, Zhenghong Hao, Shaojun Wang, Jing Xiao
This paper describes the winning system for subtask 2 and the second-placed system for subtask 1 in SemEval 2021 Task 4: ReadingComprehension of Abstract Meaning.
no code implementations • 17 Jun 2021 • Yanmeng Wang, Yanqing Xu, Qingjiang Shi, Tsung-Hui Chang
Federated learning (FL) has been recognized as a viable distributed learning paradigm which trains a machine learning model collaboratively with massive mobile devices in the wireless edge while protecting user privacy.
no code implementations • 4 Nov 2018 • Yinpei Dai, Yichi Zhang, Zhijian Ou, Yanmeng Wang, Junlan Feng
Second, the one-hot encoding of slot labels ignores the semantic meanings and relations for slots, which are implicit in their natural language descriptions.