|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | A Novel Feature-based Method for Sentiment Analysis of Chinese Product Reviews显示文摘Sentiment analysis of online reviews and other user generated content is an important research problem for its wide range of applications.In this paper,we propose a feature-based vector model and a novel weighting algorithm for sentiment analysis of Chinese product reviews.Specifically,an opinionated document is modeled by a set of feature-based vectors and corresponding weights.Different from previous work,our model considers modifying relationships between words and contains rich sentiment strength descriptions which are represented by adverbs of degree and punctuations.Dependency parsing is applied to construct the feature vectors.A novel feature weighting algorithm is proposed for supervised sentiment classification based on rich sentiment strength related information.The experimental results demonstrate the effectiveness of the proposed method compared with a state of the art method using term level weighting algorithms. | LIU Lizhen SONG Wei WANG Hanshi LI Chuchu LU Jingli | 2014 | China Communications2014，11，3： | 5 |
| 2 | Multi-Domain Collaborative Recommendation with Feature Selection显示文摘Collaborative f iltering, as one of the most popular techniques, plays an important role in recommendation systems. However,when the user-item rating matrix is sparse,its performance will be degenerate. Recently,domain-specific recommendation approaches have been developed to address this problem.The basic idea is to partition the users and items into overlapping domains, and then perform recommendation in each domain independently. Here, a domain means a group of users having similar preference to a group of products. However, these domain-specific methods consisting of two sequential steps ignore the mutual benefi t of domain segmentation and recommendation. Hence, a unified framework is presented to simultaneously realize recommendation and make use of the domain information underlying the rating matrix in this paper. Based on matrix factorization,the proposed model learns both user preferences of multiple domains and preference selection vectors to select relevant features for each group of products. Besides, local context information is utilized from the user-item rating matrix to enhance the new framework.Experimental results on two widely used datasets, e.g., Ciao and Epinions, demonstrate the effectiveness of our proposed model. | Lizhen Liu Junjun Cui Wei Song Hanshi Wang | 2017 | China Communications2017，14，8： | 3 |
| 3 | A Probabilistic Rating Prediction and Explanation Inference Model for Recommender Systems显示文摘Collaborative Filtering(CF) is a leading approach to build recommender systems which has gained considerable development and popularity. A predominant approach to CF is rating prediction recommender algorithm, aiming to predict a user's rating for those items which were not rated yet by the user. However, with the increasing number of items and users, thedata is sparse.It is difficult to detectlatent closely relation among the items or users for predicting the user behaviors. In this paper,we enhance the rating prediction approach leading to substantial improvement of prediction accuracy by categorizing according to the genres of movies. Then the probabilities that users are interested in the genres are computed to integrate the prediction of each genre cluster. A novel probabilistic approach based on the sentiment analysis of the user reviews is also proposed to give intuitional explanations of why an item is recommended.To test the novel recommendation approach, a new corpus of user reviews on movies obtained from the Internet Movies Database(IMDB) has been generated. Experimental results show that the proposed framework is effective and achieves a better prediction performance. | WANG Hanshi FU Qiujie LIU Lizhen SONG Wei | 2016 | China Communications2016，13，2： | 3 |
| 4 | A new unsupervised approach to word segmentation显示文摘 | Wang Hanshi Zhu Jian Tang Shiping | 2011 | Computational Linguistics2011，37，3： | 1 |
| 5 | Some comments on the measurement of niche metrics 显示文摘 | HANSHY I | 1978 | Ecology1978，59，： | 1 |
| 6 | Uterine Artery Embolization Combined with Local Methotrexate and Systemic Methotrexate for Treatment of Cesarean Scar Pregnancy with Different Ultrasonographic Pattern显示文摘 | Fan Lian Yu Wang Wei Chen Jiaping Li Zhongping Zhan Yujin Ye Yunxiao Zhu Jia Huang Hanshi Xu Xiuyan Yang Liuqin Liang Jianyong Yang | 2012 | CardioVascular and Interventional Radiology2012，，2： | 1 |
| 7 | A new unsu- pervised word segmentation approach显示文摘 | Wang Hanshi Zhu Jian Tang Shiping | 2011 | C0mputational Linguistics2011，37，3： | 1 |
| 8 | A New Unsupervised Approach to Word Segmentation显示文摘 | Wang Hanshi Zhu Jian Tang Shiping | | 0，，03： | 1 |
| 9 | Quadruple bonding of carbon in terminal carbides显示文摘Despite its four valence electrons,carbon can at most form triple bond in ordinary organic complexes.Quadruple bonds for carbon had been considered as impossible for a long time.Recently we showed that quadruple bonding is viable in a triatomic uranium carbide oxide molecule CUO,where the terminal C is quadruply bonded with U via its nearly unhybridized 2s-and2p-orbitals.Here we extend this new concept to a series of diatomic molecules consisting of tetravalent p-,d-,and f-elements and terminal carbide.Investigation has been focused on a series of CM-type molecules with possible quadruply-bonded carbon(QBC),CB?,CTi,CZr,CHf,CV+,CNb+,CTa+,and isoelectronic species of CUO.We have performed natural bond orbital(NBO),natural resonance theory(NRT),and atom-in-molecule(AIM)analyses at both density functional theory(DFT)and ab initio CASSCF levels to provide evidence for the feasibility of carbon quadruple bond in these systems.Our calculation results show that the C?M bond orders in these QBC species are comparable to that in CUO,indicating terminal carbides can have novel quadruple bonding when appropriate orbitals are available in the adjacent atoms. | QIU YiHeng HU HanShi CHEN Guo LI Jun | 2014 | Science China Chemistry2014，57，3： | 0 |
| 10 | RGB oralscan video-based orthodontic treatment monitoring显示文摘Orthodontic treatment monitoring involves using current images and previous 3D models to estimate the relative position of individual teeth before and after orthodontic treatment.This process differs from image-based object 6D pose estimation due to the gingiva deformation and varying pose offsets for each tooth during treatment.Motivated by the fact that the poses of molars remain relatively fixed in implicit orthodontics,we design an approach that employs multiview pose evaluation and bidirectional temporal propagation for jaw pose estimation and then employs an iteration-based method for tooth alignment.To handle changes in tooth appearance or location with weak texture across frames,we also introduce an instance propagation module that leverages positional and semantic information to explore instance relations in the temporal domain.We evaluated the performance of our approach using both the Shining3D tooth pose dataset and the Aoralscan3 tooth registration dataset.Our experimental results demonstrate remarkable accuracy improvements compared with existing methods. | Yan TIAN Hanshi FU Hao WANG Yuqi LIU Zhaocheng XU Hong CHEN Jianyuan LI Ruili WANG | 2024 | Science China(Information Sciences)2024，67，1： | 0 |
| 11 | An Improved Unsupervised Approach to Word Segmentation显示文摘ESA is an unsupervised approach to word segmentation previously proposed by Wang, which is an iterative process consisting of three phases: Evaluation, Selection and Adjustment. In this article, we propose Ex ESA, the extension of ESA. In Ex ESA, the original approach is extended to a 2-pass process and the ratio of different word lengths is introduced as the third type of information combined with cohesion and separation. A maximum strategy is adopted to determine the best segmentation of a character sequence in the phrase of Selection. Besides, in Adjustment, Ex ESA re-evaluates separation information and individual information to overcome the overestimation frequencies. Additionally, a smoothing algorithm is applied to alleviate sparseness. The experiment results show that Ex ESA can further improve the performance and is time-saving by properly utilizing more information from un-annotated corpora. Moreover, the parameters of Ex ESA can be predicted by a set of empirical formulae or combined with the minimum description length principle. | WANG Hanshi HAN Xuhong LIU Lizhen SONG Wei YUAN Mudan | 2015 | China Communications2015，12，7： | 0 |
| 12 | Reconstruction Paleoclimate Dased on Sporopollen Record of Re'nacuo Lake,Tibet显示文摘The sedimentary sequences since 33 ka B.P.to 10 ka B.P.have been established in the Re'nacuo-Lake,Gaize area of north Tibet,through a study of a lacustrine section.The climate since 33 ka B.P.to 10 ka B.P.may be divided into two cycle include 5 dry phases and 5 moist phases from reconstructing the paleoclimate through a study of sporopollen analysis.It mainly reflects the general regularity of global climatic change through contrasting with the pale environment in northern hemisphere.Our pollen record reveals a regional climate history similar to those from the neighboring sites,including the GISP2,the Guliya ice core and core RM in Zoige,and thus supports the notion that the Qinghai-Tibetan Plateau acts as an important link between climatic events in the North Atlantic realm and the Asian monsoon domain.The response of the Qinghai-Tibet Plateau to the global climatic change is relatively sensitive. | LI Hanshi WANG Genhou YUAN Guoli FANG Bin LUO Tongwei YANG Yongqiang | 2014 | Acta Geologica Sinica(English Edition)2014，88，4： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员