|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Masked Sentence Model Based on BERT for Move Recognition in Medical Scientific Abstracts显示文摘Purpose:Mo ve recognition in scientific abstracts is an NLP task of classifying sentences of the abstracts into different types of language units.To improve the performance of move recognition in scientific abstracts,a novel model of move recognition is proposed that outperforms the BERT-based method.Design/methodology/approach:Prevalent models based on BERT for sentence classification often classify sentences without considering the context of the sentences.In this paper,inspired by the BERT masked language model(MLM),we propose a novel model called the masked sentence model that integrates the content and contextual information of the sentences in move recognition.Experiments are conducted on the benchmark dataset PubMed 20K RCT in three steps.Then,we compare our model with HSLN-RNN,BERT-based and SciBERT using the same dataset.Findings:Compared with the BERT-based and SciBERT models,the F1 score of our model outperforms them by 4.96%and 4.34%,respectively,which shows the feasibility and effectiveness of the novel model and the result of our model comes closest to the state-of-theart results of HSLN-RNN at present.Research limitations:The sequential features of move labels are not considered,which might be one of the reasons why HSLN-RNN has better performance.Our model is restricted to dealing with biomedical English literature because we use a dataset from PubMed,which is a typical biomedical database,to fine-tune our model.Practical implications:The proposed model is better and simpler in identifying move structures in scientific abstracts and is worthy of text classification experiments for capturing contextual features of sentences.Originality/value:T he study proposes a masked sentence model based on BERT that considers the contextual features of the sentences in abstracts in a new way.The performance of this classification model is significantly improved by rebuilding the input layer without changing the structure of neural networks. | Gaihong Yu Zhixiong Zhang Huan Liu Liangping Ding | 2019 | Journal of Data and Information Science2019，4，4： | 14 |
| 2 | Automatic Keyphrase Extraction from Scientific Chinese Medical Abstracts Based on Character-Level Sequence Labeling显示文摘Purpose:Automatic keyphrase extraction(AKE)is an important task for grasping the main points of the text.In this paper,we aim to combine the benefits of sequence labeling formulation and pretrained language model to propose an automatic keyphrase extraction model for Chinese scientific research.Design/methodology/approach:We regard AKE from Chinese text as a character-level sequence labeling task to avoid segmentation errors of Chinese tokenizer and initialize our model with pretrained language model BERT,which was released by Google in 2018.We collect data from Chinese Science Citation Database and construct a large-scale dataset from medical domain,which contains 100,000 abstracts as training set,6,000 abstracts as development set and 3,094 abstracts as test set.We use unsupervised keyphrase extraction methods including term frequency(TF),TF-IDF,TextRank and supervised machine learning methods including Conditional Random Field(CRF),Bidirectional Long Short Term Memory Network(BiLSTM),and BiLSTM-CRF as baselines.Experiments are designed to compare word-level and character-level sequence labeling approaches on supervised machine learning models and BERT-based models.Findings:Compared with character-level BiLSTM-CRF,the best baseline model with F1 score of 50.16%,our character-level sequence labeling model based on BERT obtains F1 score of 59.80%,getting 9.64%absolute improvement.Research limitations:We just consider automatic keyphrase extraction task rather than keyphrase generation task,so only keyphrases that are occurred in the given text can be extracted.In addition,our proposed dataset is not suitable for dealing with nested keyphrases.Practical implications:We make our character-level IOB format dataset of Chinese Automatic Keyphrase Extraction from scientific Chinese medical abstracts(CAKE)publicly available for the benefits of research community,which is available at:http://gffzz188fe103f8f1460asqxoxko9fukn96kwx.ffgz.tsg.suse.edu.cn/possible1402/Dataset-For-Chinese-Medical-Keyphrase-Extraction.Originality/value:By designing comparative experiments,our study demonstrates that character-level formulation is more suitable for Chinese automatic keyphrase extraction task under the general trend of pretrained language models.And our proposed dataset provides a unified method for model evaluation and can promote the development of Chinese automatic keyphrase extraction to some extent. | Liangping Ding Zhixiong Zhang Huan Liu Jie Li GaihongYu | 2021 | Journal of Data and Information Science2021，6，3： | 3 |
| 3 | CFD simulation on evacuation of a high-speed train continue-to-roll during long tunnel fires显示文摘 | XIE Xiongyao DING Liangping LI Yongsheng | 2010 | Journal of Tongji University (Natural Science Edition)2010，38，12： | 1 |
| 4 | Multifunctional chitosan/gelatin@tannic acid cryogels decorated with in situ reduced silver nanoparticles for wound healing显示文摘Background:Most traditional wound dressings only partially meet the needs of wound healing because of their single function.Patients usually suffer from the increasing cost of treatment and pain resulting from the frequent changing of wound dressings.Herein,we have developed a mutifunctional cryogel to promote bacterial infected wound healing based on a biocompatible polysaccharide.Methods:The multifunctional cryogel is made up of a compositive scaffold of chitosan(CS),gelatin(Gel)and tannic acid(TA)and in situ formed silver nanoparticles(Ag NPs).A liver bleeding rat model was used to evaluate the dynamic hemostasis performance of the various cryogels.In order to evaluate the antibacterial properties of the prepared cryogels,gram-positive bacterium Staphylococcus aureus(S.aureus)and gram-negative bacterium Escherichia coli(E.coli)were cultured with the cryogels for 12 h.Meanwhile,S.aureus was introduced to cause bacterial infection in vivo.After treatment for 2 days,the exudates from wound sites were dipped for bacterial colony culture.Subsequently,the anti-inflammatory effect of the various cryogels was evaluated by western blotting and enzyme-linked immunosorbent assay.Finally,full-thickness skin defect models on the back of SD rats were established to assess the wound healing performances of the cryogels.Results:Due to its porous structure,the multifunctional cryogel showed fast liver hemostasis.The introduced Ag NPs endowed the cryogel with an antibacterial efficiency of>99.9%against both S.aureus and E.coli.Benefited from the polyphenol groups of TA,the cryogel could inhibit nuclear factor-κB nuclear translocation and down-regulate inflammatory cytokines for an anti-inflammatory effect.Meanwhile,excessive reactive oxygen species could also be scavenged effectively.Despite the presence of Ag NPs,the cryogel did not show cytotoxicity and hemolysis.Moreover,in vivo experiments demonstrated that the biocompatible cryogel displayed effective bacterial disinfection and accelerated wound healing.Conclusions:The multifunctional cryogel,with fast hemostasis,antibacterial and anti-inflammation properties and the ability to promote cell proliferation could be widely applied as a wound dressing for bacterial infected wound healing. | Na Xu Yucheng Yuan Liangping Ding Jiangfeng Li Jiezhi Jia Zheng Li Dengfeng He Yunlong Yu | 2022 | Burns & Trauma2022，10，1： | 1 |
| 5 | Mediastinal Tuberculoma Mimicking Malignant Cardiac Tumor:A Case Report显示文摘Background:The clinical manifestations of cardiac masses are diverse and lack specifi city.Here we report a cardiac mass detected by transthoracic echocardiography.Multimodality imaging and pathological fi ndings after the operation confi rmed the mass as mediastinal tuberculoma.Case presentation:A 45-year-old male patient was admitted to our hospital reporting chest tightness,weight loss,and dyspnea for 3 months after exercise.Transthoracic echocardiography showed that there were a large number of pericardial effusions and a soft tissue mass measuring 7.7 cm×4.5 cm in the upper mediastinum,which oppressed the right pulmonary artery and accelerated the blood fl ow of the left pulmonary artery.Contrast-enhanced ultrasonography showed degenerative inhomogeneous high enhancement of and an unclear boundary in the mass.Contrast-enhanced chest CT revealed punctate and patchy calcifi cation in and uneven enhancement of the mass and the lymph nodes around the aortic arch.The mass was diagnosed as a malignant mediastinal tumor.Pathological analysis of the mass revealed chronic granulomatous tuberculosis.The symptoms abated signifi cantly after antituberculosis treatment.The patient remained asymptomatic during follow-up.Conclusion:This report presents a rare case of mediastinal tuberculoma mimicking a malignant cardiac tumor.Multimodality imaging should be incorporated for differentiation of cardiac masses. | Yiqian Ding Wei Li Yanqiu Liu Min Ye Liangping Cheng Donghong Liu Hong Lin Fengjuan Yao | 2021 | Cardiovascular Innovations and Applications2021，，2： | 0 |
| 6 | Probing surface structure on two-dimensional metal-organic layers to understand suppressed interlayer packing显示文摘Two-dimensional metal-organic layers(MOLs)from alternatively connected benzene-tribenzoate ligands and Zr6(μ3-O)_(4)(μ3-OH)_(4) or Hf6(μ3-O)_(4)(μ3-OH)_(4) secondary building units can be prepared in gram scale via solvothermal synthesis.However,the reason why the monolayers did not pack to form thick crystals is unknown.Here we investigated the surface structure of the MOLs by a combination of sum-frequency generation spectroscopy,nanoscale infrared microscopy,atomic force microscopy,aberration-corrected transmission electron microscopy,and compositional analysis.We found a partial coverage of the monolayer surface by dangling tricarboxylate ligands,which prevent packing of the monolayers.This finding illustrates low-density surface modification as a strategy to prepare new two-dimensional materials with a high percentage of exposed surface. | Peican Chen Yi Liu Xuefu Hu Xiaolin Liu En-Ming You Xudong Qian Jiawei Chen Liangping Xiao Lingyun Cao Xinxing Peng Zhongming Zeng Yibing Jiang Song-Yuan Ding Honggang Liao Zhaohui Wang Da Zhou Cheng Wang | 2020 | Nano Research2020，13，11： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员