Search

Your search keyword '"Yang An Wen"' showing total 7,921 results
Start Over Author "Yang An Wen"
7,921 results on '"Yang An Wen"'

501. Resolving Regular Polysemy in Named Entities

Author

Hsieh, Shu-Kai, Tseng, Yu-Hsiang, Chou, Hsin-Yu, Yang, Ching-Wen, Chang, Yu-Yun, Hsieh, Shu-Kai, Tseng, Yu-Hsiang, Chou, Hsin-Yu, Yang, Ching-Wen, and Chang, Yu-Yun

Abstract

Word sense disambiguation primarily addresses the lexical ambiguity of common words based on a predefined sense inventory. Conversely, proper names are usually considered to denote an ad-hoc real-world referent. Once the reference is decided, the ambiguity is purportedly resolved. However, proper names also exhibit ambiguities through appellativization, i.e., they act like common words and may denote different aspects of their referents. We proposed to address the ambiguities of proper names through the light of regular polysemy, which we formalized as dot objects. This paper introduces a combined word sense disambiguation (WSD) model for disambiguating common words against Chinese Wordnet (CWN) and proper names as dot objects. The model leverages the flexibility of a gloss-based model architecture, which takes advantage of the glosses and example sentences of CWN. We show that the model achieves competitive results on both common and proper nouns, even on a relatively sparse sense dataset. Aside from being a performant WSD tool, the model further facilitates the future development of the lexical resource.

Published
2024

502. A Large-Scale Evaluation of Speech Foundation Models

Author

Yang, Shu-wen, Chang, Heng-Jui, Huang, Zili, Liu, Andy T., Lai, Cheng-I, Wu, Haibin, Shi, Jiatong, Chang, Xuankai, Tsai, Hsiang-Sheng, Huang, Wen-Chin, Feng, Tzu-hsun, Chi, Po-Han, Lin, Yist Y., Chuang, Yung-Sung, Huang, Tzu-Hsien, Tseng, Wei-Cheng, Lakhotia, Kushal, Li, Shang-Wen, Mohamed, Abdelrahman, Watanabe, Shinji, Lee, Hung-yi, Yang, Shu-wen, Chang, Heng-Jui, Huang, Zili, Liu, Andy T., Lai, Cheng-I, Wu, Haibin, Shi, Jiatong, Chang, Xuankai, Tsai, Hsiang-Sheng, Huang, Wen-Chin, Feng, Tzu-hsun, Chi, Po-Han, Lin, Yist Y., Chuang, Yung-Sung, Huang, Tzu-Hsien, Tseng, Wei-Cheng, Lakhotia, Kushal, Li, Shang-Wen, Mohamed, Abdelrahman, Watanabe, Shinji, and Lee, Hung-yi

Abstract

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech. We propose a unified multi-tasking framework to address speech processing tasks in SUPERB using a frozen foundation model followed by task-specialized, lightweight prediction heads. Combining our results with community submissions, we verify that the foundation model paradigm is promising for speech, and our multi-tasking framework is simple yet effective, as the best-performing foundation model shows competitive generalizability across most SUPERB tasks. For reproducibility and extensibility, we have developed a long-term maintained platform that enables deterministic benchmarking, allows for result sharing via an online leaderboard, and promotes collaboration through a community-driven benchmark database to support new development cycles. Finally, we conduct a series of analyses to offer an in-depth understanding of SUPERB and speech foundation models, including information flows across tasks inside the models, the correctness of the weighted-sum benchmarking protocol and the statistical significance and robustness of the benchmark., Comment: The extended journal version for SUPERB and SUPERB-SG. Published in IEEE/ACM TASLP. The Arxiv version is preferred

Published
2024

509. Accurate inference of isoforms from multiple sample RNA-Seq data

Author

Tasnim, Masruba, Ma, Shining, Yang, Ei-Wen, Jiang, Tao, and Li, Wei

Subjects
Biological Sciences, Bioinformatics and Computational Biology, Genetics, Bioengineering, Human Genome, Algorithms, Alternative Splicing, Animals, Computational Biology, Computer Simulation, Gene Expression Profiling, Humans, Internet, Models, Genetic, Protein Isoforms, Reproducibility of Results, Sequence Analysis, RNA, Software, Transcriptome, Information and Computing Sciences, Medical and Health Sciences, Bioinformatics, Biological sciences, Biomedical and clinical sciences
Abstract

BackgroundRNA-Seq based transcriptome assembly has become a fundamental technique for studying expressed mRNAs (i.e., transcripts or isoforms) in a cell using high-throughput sequencing technologies, and is serving as a basis to analyze the structural and quantitative differences of expressed isoforms between samples. However, the current transcriptome assembly algorithms are not specifically designed to handle large amounts of errors that are inherent in real RNA-Seq datasets, especially those involving multiple samples, making downstream differential analysis applications difficult. On the other hand, multiple sample RNA-Seq datasets may provide more information than single sample datasets that can be utilized to improve the performance of transcriptome assembly and abundance estimation, but such information remains overlooked by the existing assembly tools.ResultsWe formulate a computational framework of transcriptome assembly that is capable of handling noisy RNA-Seq reads and multiple sample RNA-Seq datasets efficiently. We show that finding an optimal solution under this framework is an NP-hard problem. Instead, we develop an efficient heuristic algorithm, called Iterative Shortest Path (ISP), based on linear programming (LP) and integer linear programming (ILP). Our preliminary experimental results on both simulated and real datasets and comparison with the existing assembly tools demonstrate that (i) the ISP algorithm is able to assemble transcriptomes with a greatly increased precision while keeping the same level of sensitivity, especially when many samples are involved, and (ii) its assembly results help improve downstream differential analysis. The source code of ISP is freely available at http://alumni.cs.ucr.edu/~liw/isp.html.

Published
2015

510. Investigation of water-retention and uniaxial compression behaviour of MX80 bentonite pellet at various suctions

Author

Yang Jin-Wen, Cui Yu-Jun, and Mokni Nadia

Subjects
Environmental sciences, GE1-350
Abstract

MX80 bentonite pellet/powder mixture has been regarded as a candidate sealing material in deep geological high-level radioactive waste disposal. As single pellet plays an important role in the global hydromechanical behaviour of the mixture, a series of single pellet compression tests were conducted on cylindershape MX80 bentonite 32-mm pellet after reaching suction equilibrium. The changes in volume and water content during the suction equilibration with the vapour equilibrium technique allowed the water-retention properties to be investigated. X-ray μCT observations were also made on pellets after reaching the target suctions. Results showed that upon drying the water content, void ratio and volumetric strain decreased slightly, but increased significantly upon wetting. Moreover, upon drying the network of cracks presented insignificant change and the cracks were mainly located in the marginal areas of pellet, while on wetting, cracks substantially propagated from the marginal areas to the core of pellet. The uniaxial compression tests on single pellets showed that the axial strain εaxial contributed to the contractancy, while the lateral strain εlateral to the dilatancy. The uniaxial shear strength σa, max, the crack closure (CC) stress σcc, the crack initiation (CI) stress σci, the crack damage (CD) stress σcd and the Young’s modulus E were found to decrease with suction decreasing, evidencing the suction effect through softening and cracking. Because of the combined effect of suction and wetting-induced cracks, the Poisson’s ratios v increased until the suction decreased to 38-25 MPa, and then decreased with further suction decrease. Uniaxial loading closed the horizontal wetting-induced cracks at suctions ≤ 9 MPa, leading to a drop of εlateral before CC.

Published
2023
Full Text
View/download PDF

522. Acupuncture for persistent atrial fibrillation after catheter ablation: study protocol for a pilot randomized controlled trial

Author

Lin, Ying, Wang, Xian, Li, Xue-Bin, Wu, Bang-Qi, Zhang, Zhao-Hui, Guo, Wei-Hua, Wu, Cun-Cao, Chen, Xin, Chen, Ming-Long, Dai, Zhong, Chen, Fu-Yan, Zhu, Rui, Liang, Chu-Xi, Tian, Yun-Peng, Yang, Gang, Yan, Chao-Qun, Lu, Jing, Wang, Hai-Ying, Li, Jin-Ling, Tu, Jian-Feng, Li, He-Wen, Yang, Dan-Dan, Yu, Fang-Ting, Wang, Yu, Yang, Jing-Wen, Shi, Guang-Xia, Yan, Shi-Yan, Wang, Li-Qiong, and Liu, Cun-Zhi

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results