Aspect-BasedSentimentClassification(ABSC)属于细粒度情感分析任务之一,旨在发现实体方面(Aspect)相关的情感倾向.本论文中提出一种基于胶囊网络的模型:MADC(Model based on Asp-Routing and Doc-Routing Capsule),通过迁移模型将文...Aspect-BasedSentimentClassification(ABSC)属于细粒度情感分析任务之一,旨在发现实体方面(Aspect)相关的情感倾向.本论文中提出一种基于胶囊网络的模型:MADC(Model based on Asp-Routing and Doc-Routing Capsule),通过迁移模型将文档级别的特征和语义信息用于方面级情感分析中,针对文档级别和句子级别的的任务,分别使用了基于注意力机制的AspRouting和Doc-Routing动态路由方法,加强了句子级别任务情感分析的可信度.为了让模型识别特定领域词向量的语义信息,文章使用双嵌入词向量加位置信息的表示方法,通过卷积神经网络抽取特征作为胶囊网络的输入,再使用两层动态路由算法使网络共享迁移学习的特征胶囊和主胶囊,最后针对不同的任务使用不同的类胶囊输出向量对方面情感或文档级别情感作出极性预测.文章通过在数据集上与多个框架的对比论证了模型的有效性.展开更多
Copy deterrence is a digital watermarking application which enables a seller to identify the buyers who obtain digital content legally but illegally redistribute it. However, in many buyer-seller watermarking protocol...Copy deterrence is a digital watermarking application which enables a seller to identify the buyers who obtain digital content legally but illegally redistribute it. However, in many buyer-seller watermarking protocols proposed for copy deterrence, the seller has to embed two watermarks into each copy of the digital content before it is sold. In this paper, we propose a new buyer-seller watermarking protocol in which the seller can reduce the number of the embedded watermarks from two to one. The proposed protocol also provides a more efficient solution to the unbinding problem than that of Lei et al＇s scheme.展开更多
Objective:To explore the clinical efficacy of plastic surgery of asymmetric double eyelid.Methods:The clinical data of 70 patients with asymmetrical double eyelid who underwent plastic surgery in our hospital from Apr...Objective:To explore the clinical efficacy of plastic surgery of asymmetric double eyelid.Methods:The clinical data of 70 patients with asymmetrical double eyelid who underwent plastic surgery in our hospital from April 2018 to December 2019 were retrospectively analyzed.The patients were divided into different groups based on different plastic surgery procedures.The control group(n=35 cases)were the patients who underwent double eyelid incision method,and the patients who used embedding double eyelid method were included in the observation group(n=35 cases).The operation time,intraoperative blood loss,incision size,healing time of incision,satisfaction of p1astic surgery and occurrence of complications were compared between the two groups.Results:The operation time and incision healing time of the observation group were shorter than those of the control group.The intraoperative blood 1oss and incision were less than those of the control group,and the satisfaction was higher than that of the control group.The difference was statistically significant(P<0.05).The incidence of complications in the observation group was slightly lower than the control group,but the difference was not statistically significant(P>0.05).Conclusion:For asymmetric double eyelid,it should undergo embedding double eyelid plastic surgery,because the operation time and incision healing time are shorter.And intraoperative blood 1oss and incision size are smal1er,which can improve patient satisfaction and reduce the incidence of complications.展开更多
Patent prior art search uses dispersed information to retrieve all the relevant documents with strong ambiguity from the massive patent database. This challenging task con-sists in patent reduction and patent expansio...Patent prior art search uses dispersed information to retrieve all the relevant documents with strong ambiguity from the massive patent database. This challenging task con-sists in patent reduction and patent expansion. Existing stud-ies on patent reduction ignore the relevance between techni-cal characteristics and technical domains, and result in am-biguous queries. Works on patent expansion expand terms from external resource by selecting words with similar dis-tribution or similar semantics. However, this splits the rele-vance between the distribution and semantics of the terms. Besides, common repository hardly meets the requirement of patent expansion for uncommon semantics and unusual terms. In order to solve these problems, we first present a novel composite-domain perspective model which converts the technical characteristic of a query patent to a specific composite classified domain and generates aspect queries. We then implement patent expansion with double consistency by combining distribution and semantics simultaneously. We also propose to train semantic vector spaces via word em-bedding under the specific classified domains, so as to pro-vide domain-aware expanded resource. Finally, multiple re-trieval results of the same topic are merged based on perspec-tive weight and rank in the results. Our experimental results on CLEP-IP 2010 demonstrate that our method is very effec-tive. It reaches about 5.43% improvement in recall and nearly 12.38% improvement in PRES over the state-of-the-art. Our work also achieves the best performance balance in terms of recall, MAP and PRES.展开更多
文摘Aspect-BasedSentimentClassification(ABSC)属于细粒度情感分析任务之一,旨在发现实体方面(Aspect)相关的情感倾向.本论文中提出一种基于胶囊网络的模型:MADC(Model based on Asp-Routing and Doc-Routing Capsule),通过迁移模型将文档级别的特征和语义信息用于方面级情感分析中,针对文档级别和句子级别的的任务,分别使用了基于注意力机制的AspRouting和Doc-Routing动态路由方法,加强了句子级别任务情感分析的可信度.为了让模型识别特定领域词向量的语义信息,文章使用双嵌入词向量加位置信息的表示方法,通过卷积神经网络抽取特征作为胶囊网络的输入,再使用两层动态路由算法使网络共享迁移学习的特征胶囊和主胶囊,最后针对不同的任务使用不同的类胶囊输出向量对方面情感或文档级别情感作出极性预测.文章通过在数据集上与多个框架的对比论证了模型的有效性.
基金the National Natural Science Foundation of China (Nos. 60970110, 60972034 and 60773086)the National Basic Research Program (973) of China(No. 2007CB311201)the Shanghai Leading Academic Discipline Project (No. B412)
文摘Copy deterrence is a digital watermarking application which enables a seller to identify the buyers who obtain digital content legally but illegally redistribute it. However, in many buyer-seller watermarking protocols proposed for copy deterrence, the seller has to embed two watermarks into each copy of the digital content before it is sold. In this paper, we propose a new buyer-seller watermarking protocol in which the seller can reduce the number of the embedded watermarks from two to one. The proposed protocol also provides a more efficient solution to the unbinding problem than that of Lei et al＇s scheme.
文摘Objective:To explore the clinical efficacy of plastic surgery of asymmetric double eyelid.Methods:The clinical data of 70 patients with asymmetrical double eyelid who underwent plastic surgery in our hospital from April 2018 to December 2019 were retrospectively analyzed.The patients were divided into different groups based on different plastic surgery procedures.The control group(n=35 cases)were the patients who underwent double eyelid incision method,and the patients who used embedding double eyelid method were included in the observation group(n=35 cases).The operation time,intraoperative blood loss,incision size,healing time of incision,satisfaction of p1astic surgery and occurrence of complications were compared between the two groups.Results:The operation time and incision healing time of the observation group were shorter than those of the control group.The intraoperative blood 1oss and incision were less than those of the control group,and the satisfaction was higher than that of the control group.The difference was statistically significant(P<0.05).The incidence of complications in the observation group was slightly lower than the control group,but the difference was not statistically significant(P>0.05).Conclusion:For asymmetric double eyelid,it should undergo embedding double eyelid plastic surgery,because the operation time and incision healing time are shorter.And intraoperative blood 1oss and incision size are smal1er,which can improve patient satisfaction and reduce the incidence of complications.
基金This work was supported by the National Natural Science Foundation of China (Grant Nos. 61232002, 61572376)the Science and Technology Support Program of Hubei Province (2015BAA127)the Wuhan Innovation Team Project (2014070504020237).
文摘Patent prior art search uses dispersed information to retrieve all the relevant documents with strong ambiguity from the massive patent database. This challenging task con-sists in patent reduction and patent expansion. Existing stud-ies on patent reduction ignore the relevance between techni-cal characteristics and technical domains, and result in am-biguous queries. Works on patent expansion expand terms from external resource by selecting words with similar dis-tribution or similar semantics. However, this splits the rele-vance between the distribution and semantics of the terms. Besides, common repository hardly meets the requirement of patent expansion for uncommon semantics and unusual terms. In order to solve these problems, we first present a novel composite-domain perspective model which converts the technical characteristic of a query patent to a specific composite classified domain and generates aspect queries. We then implement patent expansion with double consistency by combining distribution and semantics simultaneously. We also propose to train semantic vector spaces via word em-bedding under the specific classified domains, so as to pro-vide domain-aware expanded resource. Finally, multiple re-trieval results of the same topic are merged based on perspec-tive weight and rank in the results. Our experimental results on CLEP-IP 2010 demonstrate that our method is very effec-tive. It reaches about 5.43% improvement in recall and nearly 12.38% improvement in PRES over the state-of-the-art. Our work also achieves the best performance balance in terms of recall, MAP and PRES.
