1 code implementation • ACL 2022 • Timothy Liu, De Wen Soh
To effectively characterize the nature of paraphrase pairs without expert human annotation, we proposes two new metrics: word position deviation (WPD) and lexical deviation (LD).
no code implementations • 17 Oct 2023 • Huiming Wang, Liying Cheng, Zhaodonghui Li, De Wen Soh, Lidong Bing
However, to train a contrastive learning model, large numbers of labeled sentences are required to construct positive and negative pairs explicitly, such as those in natural language inference (NLI) datasets.
no code implementations • 10 Sep 2023 • Qi Zhang, Jiang Zhu, Fengzhong Qu, De Wen Soh
To overcome this fundamental bottleneck, we propose a one-bit-aided (1bit-aided) modulo sampling scheme for direction-of-arrival (DOA) estimation.
no code implementations • 19 May 2023 • Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, Lidong Bing
Recently, data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER).
no code implementations • 28 Oct 2022 • Qi Zhang, Jiang Zhu, Fengzhong Qu, De Wen Soh
In addition, a two-stage US LSE (USLSE) is proposed, where the line spectral signal is first recovered by iteratively executing DP and OMP, and then the parameters are estimated by applying a state-of-the-art LSE algorithm.
no code implementations • 5 Mar 2021 • Yanli Yuan, De Wen Soh, Xiao Yang, Kun Guo, Tony Q. S. Quek
Theoretically, we provide a theoretical analysis of the proposed graph estimator, which establishes a non-asymptotic bound of the estimation error under the high-dimensional setting and reflects the effect of several key factors on the convergence rate of our algorithm.
no code implementations • NeurIPS 2014 • De Wen Soh, Sekhar C. Tatikonda
The global Markov property for Gaussian graphical models ensures graph separation implies conditional independence.