Zobrazeno 1 - 10
of 886
pro vyhledávání: '"Wu, Dayong"'
Nowadays, data augmentation through synthetic data has been widely used in the field of Grammatical Error Correction (GEC) to alleviate the problem of data scarcity. However, these synthetic data are mainly used in the pre-training phase rather than
Externí odkaz:
http://arxiv.org/abs/2406.17456
Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods based on voting can effectively mitigate over-correction and improve the precision of the GEC system. However, these m
Externí odkaz:
http://arxiv.org/abs/2403.17413
Recently, much Chinese text error correction work has focused on Chinese Spelling Check (CSC) and Chinese Grammatical Error Diagnosis (CGED). In contrast, little attention has been paid to the complicated problem of Chinese Semantic Error Diagnosis (
Externí odkaz:
http://arxiv.org/abs/2305.05183
In this paper, we present an overview of the CTC 2021, a Chinese text correction task for native speakers. We give detailed descriptions of the task definition and the data for training as well as evaluation. We also summarize the approaches investig
Externí odkaz:
http://arxiv.org/abs/2208.05681
Existing Chinese text error detection mainly focuses on spelling and simple grammatical errors. These errors have been studied extensively and are relatively simple for humans. On the contrary, Chinese semantic errors are understudied and more comple
Externí odkaz:
http://arxiv.org/abs/2204.07464
Multilingual pre-trained language models have shown impressive performance on cross-lingual tasks. It greatly facilitates the applications of natural language processing on low-resource languages. However, there are still some languages that the curr
Externí odkaz:
http://arxiv.org/abs/2202.13558
Autor:
Wang, Baoxin, Meng, Qingye, Wang, Ziyue, Zhao, Honghong, Wu, Dayong, Che, Wanxiang, Wang, Shijin, Chen, Zhigang, Liu, Cong
Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs. Distance-based methods show promising performance on link prediction task, which predicts the result by the distance between two entity rep
Externí odkaz:
http://arxiv.org/abs/2202.04897
Autor:
Guo, Yameng, Zhao, Jinman, Wu, Dayong, Ma, Sida, Wang, Yandong, Zhang, Yangsheng, Ma, Haikun, Kang, Jie, Dong, Huicong, Su, Ru
Publikováno v:
In Journal of Alloys and Compounds 30 August 2024 997
Autor:
Denlinger, Nathan, Song, No-Joon, Zhang, Xiaoli, Jeon, Hyeongseon, Peterson, Chelsea, Wang, Yi, Reynolds, Kelsi, Bolz, Robert M., Miao, Jessica, Song, Chunhua, Wu, Dayong, Chan, Wing Keung, Bezerra, Evandro, Epperla, Narendranath, Voorhees, Timothy J., Brammer, Jonathan, Kittai, Adam S., Bond, David A., Sawalha, Yazeed, Sigmund, Audrey, Reneau, John C., Rubinstein, Mark P., Hanel, Walter, Christian, Beth, Baiocchi, Robert A., Maddocks, Kami, Alinari, Lapo, Vasu, Sumithira, de Lima, Marcos, Chung, Dongjun, Jaglowski, Samantha, Li, Zihai, Huang, Xiaopei, Yang, Yiping
Publikováno v:
In Blood Advances 25 June 2024 8(12):3140-3153
Autor:
Dong, Huicong, Chen, Yinghao, Wu, Dayong, Ma, Haikun, Wang, Qian, Feng, Zhihao, You, Baocai, Jia, Chonglin, Su, Ru
Publikováno v:
In Materials Chemistry and Physics 15 October 2024 326