4,023 Hits in 4.6 sec

Term Weighting Evaluation in Bipartite Partitioning for Text Clustering [chapter]

Chao Qu, Yong Li, Jun Zhu, Peican Huang, Ruifen Yuan, Tianming Hu
Information Retrieval Technology  
In this paper, we conducted an comprehensive evaluation of six variants of tf /idf factor as term weighting schemes in bipartite partitioning.  ...  To alleviate the problem of high dimensions in text clustering, an alternative to conventional methods is bipartite partitioning, where terms and documents are modeled as vertices on two sides respectively  ...  This work was partially supported by the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry of China, and the Dongguan Foundation of Scientific and Technological  ... 
doi:10.1007/978-3-540-68636-1_38 dblp:conf/airs/QuLZHYH08 fatcat:66ocobcozzgxpp6dlkegmdvbou

Web Image Clustering with Reduced Keywords and Weighted Bipartite Spectral Graph Partitioning [chapter]

Su Ming Koh, Liang-Tien Chia
2006 Lecture Notes in Computer Science  
We also propose weights for the bipartite spectral graph by using hierarchical term frequency-inverse document frequency (tf-idf).  ...  Experimental data show that this weighted bipartite spectral graph performs better than the bipartite spectral graph with a unity weight. We further exploit the tf-idf weights in merging the clusters.  ...  Beil in [7] introduced a frequent term-based text clustering method, which uses frequent terms instead of all keywords for text clustering.  ... 
doi:10.1007/11922162_100 fatcat:rksjuzk5ojbzjcj6azb2xvk4qe

Graph theoretical framework for simultaneously integrating visual and textual features for efficient web image clustering

Manjeet Rege, Ming Dong, Jing Hua
2008 Proceeding of the 17th international conference on World Wide Web - WWW '08  
However, not much work has been done in using multimodal information for clustering Web images.  ...  In this paper, we propose a graph theoretical framework for simultaneously integrating visual and textual features for efficient Web image clustering.  ...  The two data types in the co-clustering problem can be represented by the two vertices of the weighted bipartite graph. Co-clustering of the data is achieved by partitioning the bipartite graph.  ... 
doi:10.1145/1367497.1367541 dblp:conf/www/RegeDH08 fatcat:to37qv553rfyrdvmsqfczbpnym

Web image clustering by consistent utilization of visual features and surrounding texts

Bin Gao, Tie-Yan Liu, Tao Qin, Xin Zheng, Qian-Sheng Cheng, Wei-Ying Ma
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
To tackle this problem, we proposed a novel method named consistent bipartite graph co-partitioning in this paper, which can cluster Web images based on the consistent fusion of the information contained  ...  Image clustering, an important technology for image processing, has been actively researched for a long period of time.  ...  We should also thank Hang-Hang Tong, Xin-Jing WANG and Deng CAI for their enthusiasm in helping us prepare the collection of images and surrounding texts.  ... 
doi:10.1145/1101149.1101167 dblp:conf/mm/GaoLQZCM05 fatcat:xrrvnepx3bhptixmgzpz32u5am

Preserving Patterns in Bipartite Graph Partitioning

Tianming Hu, Chao Qu, Chew Tan, Sam Sung, Wenjun Zhou
2006 Proceedings - International Conference on Tools with Artificial Intelligence, TAI  
Our approach for pattern preserving clustering consists of three steps: mine maximal hyperclique patterns, form the bipartite, and partition it.  ...  This paper describes a new bipartite formulation for word-document co-clustering such that hyperclique patterns, strongly affiliated documents in this case, are guaranteed not to be split into different  ...  A recent study [33] found UPGMA to be the best in this class for clustering text. As for the partitional clustering, probably K-means is the most widely used method.  ... 
doi:10.1109/ictai.2006.97 dblp:conf/ictai/HuQTSZ06 fatcat:65x5o5zbhzhtxmgxwzuyshnf4y

Clustering web images with multi-modal features

Manjeet Rege, Ming Dong, Jing Hua
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
ABSTRACf Web image clustering has drawn significant. attention in the research community recently. However, not much work has been done in using multi-modal information for clustering Web im8ges.  ...  This is actually considered as a fusion of two bipartite graphs that are partitioned simultaneously by the proposed Consistent )soperimetric High-order Co-clustering (CIHC) framework.  ...  Web images are represented using textual features in terms of the surrounding texts and captions. Images clustered based 011 these textual features are then retrieved accordingly.  ... 
doi:10.1145/1291233.1291301 dblp:conf/mm/RegeDH07 fatcat:hdqsbwbx3zaglkqqrtfwv4t77y

Co-clustering Documents and Words by Minimizing the Normalized Cut Objective Function

Charles-Edmond Bichot
2010 Journal of Mathematical Modelling and Algorithms  
The created bipartite graph is then partitioned in a way that minimizes the normalized cut objective function to produce the document clustering.  ...  This model consists in creating a bipartite graph based on word frequencies in documents, and whose vertices are both documents and words.  ...  The fusion-fission graph partitioning metaheuristic is presented in section 4. Section 5 enumerates several evaluation measures of performance for document clustering.  ... 
doi:10.1007/s10852-010-9126-0 fatcat:h2gxshsi2zg5tik4d5c7rwarqm

Co-clustering Documents and Words Using Bipartite Isoperimetric Graph Partitioning

Manjeet Rege, Ming Dong, Farshad Fotouhi
2006 IEEE International Conference on Data Mining. Proceedings  
We then propose Isoperimetric Co-clustering Algorithm (ICA) -a new method for partitioning the document-word bipartite graph.  ...  Our extensive experiments performed on publicly available datasets demonstrate the advantages of ICA over spectral approach in terms of the quality, efficiency and stability in partitioning the documentword  ...  As a result, ICARanVR lacks in consistency in terms of guranteed optimal partitioning of the bipartite graph.  ... 
doi:10.1109/icdm.2006.36 dblp:conf/icdm/RegeDF06 fatcat:2vscjupyhnck5nmshl7s5wlixa

Bipartite isoperimetric graph partitioning for data co-clustering

Manjeet Rege, Ming Dong, Farshad Fotouhi
2008 Data mining and knowledge discovery  
We then propose Isoperimetric Co-clustering Algorithm (ICA) -a new method for partitioning the bipartite graph.  ...  partitioning the bipartite graph.  ...  Experiments performed on text as well as multimedia datasets demonstrate the advantages of our approach over other approaches in terms of the quality, efficiency and stability in partitioning the bipartite  ... 
doi:10.1007/s10618-008-0091-4 fatcat:bekot5vo5jgh7lyte5xxrlpe5u


2008 International journal on artificial intelligence tools  
Also, the partitioned bipartite with co-preserved patterns naturally lends itself to different clustering-related functions in search engines.  ...  In addition, for those words and documents across several topics, it may not be proper to assign them to a single cluster.  ...  A recent study found UPGMA to be the best in this class for clustering text. 8 As for the partitional clustering, probably K-means is the most widely used method.  ... 
doi:10.1142/s0218213008003790 fatcat:ydnd3hbd75fypcrn2jcqje42gy

Co-Preserving Patterns in Bipartite Partitioning for Topic Identification [chapter]

Tianming Hu, Hui Xiong, Sam Yuan Sung
2007 Proceedings of the 2007 SIAM International Conference on Data Mining  
Also, we illustrate an application of the partitioned bipartite to search engines, returning clustered search results for keyword queries.  ...  In addition, for those words and documents across several topics, it may not be proper to assign them to a single cluster.  ...  To avoid trivial partitions, often the constraint is imposed that each part should be roughly balanced in terms of part weight wgt(V k ), which is often defined as sum of its vertex weight.  ... 
doi:10.1137/1.9781611972771.53 dblp:conf/sdm/HuXS07 fatcat:etoraohrl5allltjlm5djxtyi4

Consistent bipartite graph co-partitioning for star-structured high-order heterogeneous data co-clustering

Bin Gao, Tie-Yan Liu, Xin Zheng, Qian-Sheng Cheng, Wei-Ying Ma
2005 Proceeding of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining - KDD '05  
Actually, this case could be a very good abstract for many real-world applications, such as the co-clustering of categories, documents and terms in text mining.  ...  Accordingly, we proposed the concept of consistent bipartite graph co-partitioning, and developed an algorithm based on semi-definite programming (SDP) for efficient computation of the clustering results  ...  Anstreicher for his great generosity and enthusiasm in helping us nail down some facts on semi-definite programming.  ... 
doi:10.1145/1081870.1081879 dblp:conf/kdd/GaoLZCM05 fatcat:qrwbxw7b7vaujfb7uk3tumwpwq

Document Clustering using a New Similarity Measure based on Energy of a Bipartite Graph

G. Hannah Grace, Kalyani Desikan
2016 Indian Journal of Science and Technology  
Methods/Statistical Analysis: We have made use of bipartite representation of documents and clustered them. The proposed algorithm has been illustrated for a small document set.  ...  Objectives: This paper aims at clustering documents using a new similarity measure based on energy of a bipartite graph.  ...  terms and w ij is the weight of the i th term in the j th document.  ... 
doi:10.17485/ijst/2016/v9i40/99005 fatcat:xp3gk3ywyrh3phbxbuosdxxs3m

Belief Propagation for Maximum Coverage on Weighted Bipartite Graph and Application to Text Summarization

Hiroki Kitano, Koujin Takeda
2020 Journal of the Physical Society of Japan  
In graph theory, the task of text summarization is regarded as maximum coverage problem on bipartite graph with weighted nodes.  ...  We generalize it to weighted graph for text summarization. Then we apply our algorithm to weighted biregular random graph for verification of maximum coverage performance.  ...  Acknowledgment We are thankful to Satoshi Takabe for discussion and helpful comments. This work is supported by KAKENHI Nos. 18K11175, 19K12178.  ... 
doi:10.7566/jpsj.89.043801 fatcat:lj64b3jyizap3pmysr3ibzpaxe

Spectral Co-Clustering for Dynamic Bipartite Graphs

Derek Greene, Padraig Cunningham
2010 European Conference on Principles of Data Mining and Knowledge Discovery  
We evaluate the method on a benchmark text corpus and Web 2.0 bookmarking data.  ...  To address this issue, we propose a dynamic spectral co-clustering method for simultaneously clustering objects and features over time, as represented by successive bipartite graphs.  ...  This work is supported by Science Foundation Ireland Grant No. 08/SRC/I140 (Clique: Graph & Network Analysis Cluster)  ... 
dblp:conf/pkdd/GreenC10 fatcat:hkildgmid5eyda5ubwm7f4ifcy
« Previous Showing results 1 — 15 out of 4,023 results