Search

Your search keyword '"Han, Yaqian"' showing total 247 results
Start Over Author "Han, Yaqian"
247 results on '"Han, Yaqian"'

2. X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection

Author

Han, Yaqian, Chai, Yekun, Wang, Shuohuan, Sun, Yu, Huang, Hongyi, Chen, Guanghao, Xu, Yitong, and Yang, Yang

Subjects
Computer Science - Computation and Language
Abstract

Detecting sarcasm and verbal irony from people's subjective statements is crucial to understanding their intended meanings and real sentiments and positions in social scenarios. This paper describes the X-PuDu system that participated in SemEval-2022 Task 6, iSarcasmEval - Intended Sarcasm Detection in English and Arabic, which aims at detecting intended sarcasm in various settings of natural language understanding. Our solution finetunes pre-trained language models, such as ERNIE-M and DeBERTa, under the multilingual settings to recognize the irony from Arabic and English texts. Our system ranked second out of 43, and ninth out of 32 in Task A: one-sentence detection in English and Arabic; fifth out of 22 in Task B: binary multi-label classification in English; first out of 16, and fifth out of 13 in Task C: sentence-pair detection in English and Arabic., Comment: SemEval-2022 Task 6

Published
2022

3. ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation

Author

Shan, Bin, Han, Yaqian, Yin, Weichong, Wang, Shuohuan, Sun, Yu, Tian, Hao, Wu, Hua, and Wang, Haifeng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance. However, these models focus only on understanding tasks utilizing encoder-only architecture. In this paper, we propose ERNIE-UniX2, a unified cross-lingual cross-modal pre-training framework for both generation and understanding tasks. ERNIE-UniX2 integrates multiple pre-training paradigms (e.g., contrastive learning and language modeling) based on encoder-decoder architecture and attempts to learn a better joint representation across languages and modalities. Furthermore, ERNIE-UniX2 can be seamlessly fine-tuned for varieties of generation and understanding downstream tasks. Pre-trained on both multilingual text-only and image-text datasets, ERNIE-UniX2 achieves SOTA results on various cross-lingual cross-modal generation and understanding tasks such as multimodal machine translation and multilingual visual question answering., Comment: 13 pages, 2 figures

Published
2022

4. Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters

Author

Xiang, Yang, Wu, Zhihua, Gong, Weibao, Ding, Siyu, Mo, Xianjie, Liu, Yuang, Wang, Shuohuan, Liu, Peng, Hou, Yongshuai, Li, Long, Wang, Bin, Shi, Shaohuai, Han, Yaqian, Yu, Yue, Li, Ge, Sun, Yu, Ma, Yanjun, and Yu, Dianhai

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Distributed, Parallel, and Cluster Computing
Abstract

The ever-growing model size and scale of compute have attracted increasing interests in training deep learning models over multiple nodes. However, when it comes to training on cloud clusters, especially across remote clusters, huge challenges are faced. In this work, we introduce a general framework, Nebula-I, for collaboratively training deep learning models over remote heterogeneous clusters, the connections between which are low-bandwidth wide area networks (WANs). We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning. To balance the accuracy and communication efficiency, in Nebula-I, parameter-efficient training strategies, hybrid parallel computing methods and adaptive communication acceleration techniques are jointly applied. Meanwhile, security strategies are employed to guarantee the safety, reliability and privacy in intra-cluster computation and inter-cluster communication. Nebula-I is implemented with the PaddlePaddle deep learning framework, which can support collaborative training over heterogeneous hardware, e.g. GPU and NPU. Experiments demonstrate that the proposed framework could substantially maximize the training efficiency while preserving satisfactory NLP performance. By using Nebula-I, users can run large-scale training tasks over cloud clusters with minimum developments, and the utility of existed large pre-trained models could be further promoted. We also introduced new state-of-the-art results on cross-lingual natural language inference tasks, which are generated based upon a novel learning framework and Nebula-I., Comment: 20 pages, 10 figures, technical report

Published
2022

7. BL-B01D1, a first-in-class EGFR–HER3 bispecific antibody–drug conjugate, in patients with locally advanced or metastatic solid tumours: a first-in-human, open-label, multicentre, phase 1 study

Author

Ma, Yuxiang, Huang, Yan, Zhao, Yuanyuan, Zhao, Shen, Xue, Jinhui, Yang, Yunpeng, Fang, Wenfeng, Guo, Ye, Han, Yaqian, Yang, Kunyu, Li, Yongsheng, Yang, Jun, Fu, Zhenming, Chen, Gang, Chen, Likun, Zhou, Ningning, Zhou, Ting, Zhang, Yaxiong, Zhou, Huaqiang, Liu, Qianwen, Zhu, Yi, Zhu, Hai, Xiao, Sa, Zhang, Li, and Zhao, Hongyun

Published
2024
Full Text
View/download PDF

9. Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Author

Cheng, Qiao, Fang, Meiyuan, Han, Yaqian, Huang, Jin, and Duan, Yitao

Subjects
Computer Science - Computation and Language, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text., Comment: Accepted at the 16th International Workshop on Spoken Language Translation (IWSLT 2019)

Published
2019

12. A multicenter, retrospective study analysis: Evaluating the efficacy and safety of pembrolizumab in the first-line treatment of recurrent or metastatic head and neck squamous cell carcinoma.

Author

Hu, Man, primary, Zhang, Shichuan, additional, Han, Yaqian, additional, Wu, Hui, additional, Gao, Jin, additional, Wu, Haijun, additional, Lin, Qin, additional, Shang, Wei, additional, Li, Xia, additional, Feng, Hong, additional, Qiao, Qiao, additional, Hu, Guangyuan, additional, Yang, Kunyu, additional, Song, Xicheng, additional, Cao, Yuandong, additional, Kang, Min, additional, Wang, Ruozheng, additional, and Yu, Jinming, additional

Published
2024
Full Text
View/download PDF

14. Efficacy and Safety of Nimotuzumab in Combination with Radiotherapy or Chemoradiotherapy for Local Advanced Head and Neck Cancer: A Systematic Review and Meta-analysis

Author

Zheng, Baomin, primary, He, Meilin, additional, Han, Yaqian, additional, Jiang, Xin, additional, Ou, Xiaomin, additional, Zhang, Peng, additional, Guo, Ruyuan, additional, Li, Jingao, additional, Zhang, Ximei, additional, Qiao, Qiao, additional, Wu, Hui, additional, Hu, Man, additional, Feng, Mei, additional, Tu, Wenyong, additional, and Yi, Junlin, additional

Published
2024
Full Text
View/download PDF

26. Distribution of regional lymph nodes metastasis in 870 cases of nasopharyngeal carcinoma and the suggestions for individualized elective prophylactic neck irradiation with intensity‐modulated radiotherapy.

Author

Wang, Lei, Wu, Zheng, He, Qian, Li, Yiting, Wang, Subin, Li, Feiping, Wang, Hui, Li, Wenhui, and Han, Yaqian

Subjects
LYMPHATIC metastasis, NASOPHARYNX cancer, INTENSITY modulated radiotherapy, IRRADIATION, NECK, NASOPHARYNX tumors
Abstract

Purpose: To explore the feasibility of individualized elective prophylactic neck irradiation (iEPNI) for optimizing current approach by investigating metastatic lymph nodes (LNs) distribution in nasopharyngeal carcinoma (NPC). Materials and Methods: Records of 870 NPC patients without distant metastasis in Hunan Cancer Hospital from January 2019 to December 2019 were reviewed. LNs' locations were identified based on the 2013 guidelines. The intra‐regional lymphatic drainage (IRLD) areas included Station 1st (level VIIa and II), Station 2nd (level III and Va), and Station 3rd (level IV, Vb, and Vc). Other levels were categorized as extra‐regional areas. Results: Among the 870 patients, 94.5% cases exhibited LNs metastasis, including unilateral metastasis in 198 patients and bilateral metastasis in 624 patients. In the whole cohort, the most common involved IRLD areas were level IIb (87.1%), VIIa (80.0%), IIa (61.8%), Va (30.6%), IV (21.4%), Vb (8.9%), and Vc (1.1%). Besides, rates of LNs metastasis in Station 1st, 2nd, and 3rd were 94.3%, 61.1%, and 22.9%, respectively. Only four patients (4, 0.5%) revealed skipping metastasis among the three stations. Conclusions: Lymph node metastasis follows an organized pattern from Station 1st to 3rd with scarce skipping metastasis. A potential iEPNI strategy of prophylactic neck irradiation to the ipsilateral latter node‐negative station appears promising in NPC patients. Further prospective investigations are warranted to validate the approach. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

27. The cancer metabolic reprogramming and immune response

Author

Xia, Longzheng, Oyang, Linda, Lin, Jinguan, Tan, Shiming, Han, Yaqian, Wu, Nayiyuan, Yi, Pin, Tang, Lu, Pan, Qing, Rao, Shan, Liang, Jiaxin, Tang, Yanyan, Su, Min, Luo, Xia, Yang, Yiqing, Shi, Yingrui, Wang, Hui, Zhou, Yujuan, and Liao, Qianjin

Published
2021
Full Text
View/download PDF

30. Organoids: opportunities and challenges of cancer therapy

Author

Jiang, Xianjie, primary, Oyang, Linda, additional, Peng, Qiu, additional, Liu, Qiang, additional, Xu, Xuemeng, additional, Wu, Nayiyuan, additional, Tan, Shiming, additional, Yang, Wenjuan, additional, Han, Yaqian, additional, Lin, Jinguan, additional, Xia, Longzheng, additional, Peng, Mingjing, additional, Tang, Yanyan, additional, Luo, Xia, additional, Su, Min, additional, Shi, Yingrui, additional, Zhou, Yujuan, additional, and Liao, Qianjin, additional

Published
2023
Full Text
View/download PDF

32. Context Sensitive Word Deletion Model for Statistical Machine Translation

Author

Li, Qiang, Han, Yaqian, Xiao, Tong, Zhu, Jingbo, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Sun, Maosong, editor, Wang, Xiaojie, editor, Chang, Baobao, editor, and Xiong, Deyi, editor

Published
2017
Full Text
View/download PDF

34. Clinical significance and integrative analysis of the cuproptosis-associated genes in head and neck squamous cell carcinoma

Author

Peng, Qiu, primary, Jiang, Xianjie, additional, Tan, Shiming, additional, Xu, Xuemeng, additional, Xia, Longzheng, additional, Wu, Nayiyuan, additional, Lin, Jinguan, additional, Oyang, Linda, additional, Tang, Yanyan, additional, Peng, Mingjing, additional, Su, Min, additional, Luo, Xia, additional, Han, Yaqian, additional, Liao, Qianjin, additional, and Zhou, Yujuan, additional

Published
2023
Full Text
View/download PDF

36. The role of tripartite motif-containing 28 in cancer progression and its therapeutic potentials

Author

Yang, Yiqing, primary, Tan, Shiming, additional, Han, Yaqian, additional, Huang, Lisheng, additional, Yang, Ruiqian, additional, Hu, Zifan, additional, Tao, Yi, additional, Oyang, Linda, additional, Lin, Jinguan, additional, Peng, Qiu, additional, Jiang, Xianjie, additional, Xu, Xuemeng, additional, Xia, Longzheng, additional, Peng, Mingjing, additional, Wu, Nayiyuan, additional, Tang, Yanyan, additional, Li, Xiaoling, additional, Liao, Qianjin, additional, and Zhou, Yujuan, additional

Published
2023
Full Text
View/download PDF

39. LPLUNC1 reduces glycolysis in nasopharyngeal carcinoma cells through the PHB1 ‐p53/ c‐Myc axis

Author

Oyang, Linda, primary, Ouyang, Lei, additional, Yang, Lixia, additional, Lin, Jinguan, additional, Xia, Longzheng, additional, Tan, Shiming, additional, Wu, Nayiyuan, additional, Han, Yaqian, additional, Yang, Yiqing, additional, Li, Jian, additional, Chen, Xiaohui, additional, Tang, Yanyan, additional, Su, Min, additional, Luo, Xia, additional, Li, Jinyun, additional, Xiong, Wei, additional, Zeng, Zhaoyang, additional, Liao, Qianjin, additional, and Zhou, Yujuan, additional

Published
2022
Full Text
View/download PDF

41. Erratum to: Diffusion-Weighted Magnetic Resonance Imaging-Guided Dose Painting in Patients With Locoregionally Advanced Nasopharyngeal Carcinoma Treated With Induction Chemotherapy Plus Concurrent Chemoradiotherapy: A Randomized, Controlled Clinical Trial

Author

Fu, Shengnan, primary, Li, Yanxian, additional, Han, Yaqian, additional, Wang, Hui, additional, Chen, Yanzhu, additional, Yan, Ouying, additional, He, Qian, additional, Ma, Hongzhi, additional, Liu, Lin, additional, and Liu, Feng, additional

Published
2022
Full Text
View/download PDF

49. LPLUNC1 reduces glycolysis in nasopharyngeal carcinoma cells through the PHB1-p53/c- Myc axis

Author

Oyang, Linda, primary, Ouyang, Lei, additional, Yang, Lixia, additional, Lin, Jinguan, additional, Xia, Longzheng, additional, Tan, Shiming, additional, Wu, Nayiyuan, additional, Han, Yaqian, additional, Yang, Yiqing, additional, Li, Jian, additional, Chen, Xiaohui, additional, Tang, Yanyan, additional, Su, Min, additional, Luo, Xia, additional, Li, Jinyun, additional, Xiong, Wei, additional, Zeng, Zhaoyang, additional, Liao, Qianjin, additional, and Zhou, Yujuan, additional

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results