6,409 Hits in 4.1 sec

Enterprise text processing: a sparse matrix approach

N. Goharian, T. El-Ghazawi, D. Grossman
Proceedings International Conference on Information Technology: Coding and Computing  
We demonstrate the application of sparse matrix-vector multiplication algorithms for text storage and retrieval as a means of supporting efficient and accurate text processing.  ...  We demonstrate query processing using sparse matrix-vector multiplication algorithm.  ...  The nature of text data in a matrix format results in a very highly sparse matrix. To save space and run time, it is important to store only the non-zero elements.  ... 
doi:10.1109/itcc.2001.918768 dblp:conf/itcc/GoharianGE01 fatcat:quz5nfxrlzcsnk5zx5lgnkqzve

Clustering of text documents with keyword weighting function

A. Christy, G. Meera Gandhi, S. Vaithyasubramanian
2019 International Journal of Intelligent Enterprise  
Documents are pre-processed and relevant keywords based on their weights are grouped together.  ...  Performance of CKW is validated by clustering BBC news collection text collections.  ...  Similarity measure for text processing (SMTP) for knowledge discovery considers the presence or absence of features available in the text collection.  ... 
doi:10.1504/ijie.2019.100029 fatcat:uytmocrskffinlouuzge6kzhka

Analysis of feature selection measures for text categorisation

V. Mary Amala Bai, D. Manimegalai
2017 International Journal of Enterprise Network Management  
The curse of dimensionality has made dimension reduction an essential step in text categorisation. Feature selection is an approach for dimension reduction.  ...  Under the unsupervised approach document frequency and under the supervised approach chi-square, odds ratio, mutual information, and information gain are considered for analysis.  ...  They are well suited for term-weighted matrix which is actually a sparse matrix. For the experiments conducted, libsvm3.1 by Chang and Lin (2001) is used.  ... 
doi:10.1504/ijenm.2017.083606 fatcat:b3z6z7fatfawnp7wjpmitbsdr4

Identification of authorship of Ukrainian-language texts of journalistic style using neural networks

Maksym Lupei, Alexander Mitsa, Volodymyr Repariuk, Vasyl Sharkan
2020 Eastern-European Journal of Enterprise Technologies  
At the first stage, we convert the collection of text documents into the frequency matrix of lexemes. In the second stage, we convert the collection of text documents into a 2-dimensional matrix.  ...  It is the vectorization procedure that converts input texts into the matrix, which records the frequency parameters of a lexeme [15] .  ... 
doi:10.15587/1729-4061.2020.195041 fatcat:wzrk4dyvvncvnfpu2a7lx2k7xe

Artificial Intelligence User Support System for SAP Enterprise Resource Planning

Vladimir Vlasov, Victoria Chebotareva, Marat Rakhimov, Sergey Kruglikov
2017 International Joint Conference on the Analysis of Images, Social Networks and Texts  
The system is based on an ensemble of machine learning algorithms of multiclass text classification, providing efficient question understanding, and a special framework for evidence retrieval, providing  ...  A TDM is a sparse matrix, i.e. most of its elements are zeros. To prevent overfitting and ensure classes generalization and interpretability, we should remove sparse terms for each class.  ...  Problem Description Enterprise resource planning (ERP) is business process management software that allows organization to use a system of integrated applications to manage the business and automate many  ... 
dblp:conf/aist/VlasovCRK17 fatcat:yaidgzqihnflnfr65da3sllsju

Product Quality Detection through Manufacturing Process Based on Sequential Patterns Considering Deep Semantic Learning and Process Rules

Liguo Yao, Haisong Huang, Shih-Huan Chen
2020 Processes  
In addition, taking the data from a production enterprise in Guizhou Province as an example, the validity of the method is verified.  ...  However, the production process mainly exists in the form of text.  ...  Processes 2020, 8, 751  ... 
doi:10.3390/pr8070751 fatcat:mqd5rej53bdfpde6ebzwl5zmym

Using Business Process Models to Retrieve Information from Governing Documents

Tarjei Laegreid, Paul Christian Sandal, Jon Espen Ingvaldsen, Jon Atle Gulla
2006 Business Information Systems  
In business process models the aim is to model the same domain from a process perspective.  ...  In this project work we investigate the potential of utilizing text mining technologies together with a standard information retrieval systemt o link these two sources of information in a dynamic way.  ...  Since process descriptions in the graphical business process models tend to be short, a direct consequence is sparse query-vectors.  ... 
dblp:conf/bis/LaegreidSIG06 fatcat:g5eosmg72bgkzokph4ceehwxwy

Sparse inverse kernel Gaussian Process regression

Kamalika Das, Ashok N. Srivastava
2013 Statistical analysis and data mining  
Approximate solutions for sparse Gaussian Processes have been proposed for sparse problems.  ...  We propose a new technique for sparse Gaussian Process regression that allows us to compute a parsimonious model while preserving the interpretability of the sparsity structure in the data.  ...  Network representing a sub-matrix of the inverse covariance matrix (b) Network representing a sub-matrix of the sparse inverse covariance matrix estimated using SPI-GP Interpretability of the model is  ... 
doi:10.1002/sam.11189 fatcat:sfruhls545a77erj35wijtmptm

In-storage embedded accelerator for sparse pattern processing

Sang-Woo Jun, Huy T. Nguyen, Vijay Gadepally, Arvind
2016 2016 IEEE High Performance Extreme Computing Conference (HPEC)  
We present a novel architecture for sparse pattern processing, using flash storage with embedded accelerators.  ...  Sparse pattern processing on large data sets is the essence of applications such as document search, natural language processing, bioinformatics, subgraph matching, machine learning, and graph processing  ...  The match processing between a document-A against the whole collection can be formulated as a matrix-vector multiplication as illustrated in Figure 5 , where both the matrix and the vector are sparse.  ... 
doi:10.1109/hpec.2016.7761588 dblp:conf/hpec/JunNGA16 fatcat:geyok6k5lvenxnncs5bqwctr4e

An analysis of the graph processing landscape [article]

Miguel E. Coimbra, Alexandre P. Francisco, Luís Veiga
2021 arXiv   pre-print
The use-case of performing global computations over a graph, it is first ingested into a graph processing system from one of many digital representations.  ...  Extracting information from graphs involves processing all their elements globally, and can be done with single-machine systems (with varying approaches to hardware usage), distributed systems (either  ...  This system considers the adjacency matrix of the graph as a sparse matrix data structure.  ... 
arXiv:1911.11624v3 fatcat:t44dfa5cvfbk7exz4s2synm5z4

A Graph-Based Approach to Skill Extraction from Text

Ilkka Kivimäki, Alexander Panchenko, Adrien Dessy, Dries Verdegem, Pascal Francq, Hugues Bersini, Marco Saerens
2013 Workshop on Graph-based Methods for Natural Language Processing  
This paper presents a system that performs skill extraction from text documents. It outputs a list of professional skills that are relevant to a given input text.  ...  We make use of the texts and the hyperlink graph of Wikipedia, as well as a list of professional skills obtained from the LinkedIn social network.  ...  The process decides, whether a word or a phrase or a skill suggested by a user is actually a skill through an analysis of the text contained in the user profile pages.  ... 
dblp:conf/textgraphs/KivimakiPDVFBS13 fatcat:hsybvsjflbf4tgg43vi6nyt4u4

An Embedding Model for Predicting Roll-Call Votes

Peter Kraft, Hirsh Jain, Alexander M. Rush
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
We develop a novel embedding-based model for predicting legislative roll-call votes from bill text.  ...  These vectors are learned to correspond with pre-trained word embeddings which allows us to analyze which features in a bill text are most predictive of political support.  ...  To create our dataset, we first find a list of all votes on the full text of bills, and create a matrix of how each congressperson voted on each bill, which will be used in training and in testing.  ... 
doi:10.18653/v1/d16-1221 dblp:conf/emnlp/KraftJR16 fatcat:fsklp4grpfgatoy6fheyyse74m

Web Query Processing Approaches A Survey and Comparison

M. Manikantan, S. Duraisamy
2014 International Journal of Computer Applications  
In this survey we are discussing on each of these topics and including how synonyms adding approach and Linguistic based approach are used in web query processing.  ...  The web search is enabled by navigating hyperlinks in a webpage or through search engines or by web programming.  ...  The first step is to use the text to construct a matrix X, in which the row vectors represent words and the column vectors represent chunks of text (e.g., sentences, paragraphs, documents).  ... 
doi:10.5120/14893-3362 fatcat:qlux6724hfgpnof2k43dqrc5gq

Research on professional talent training technology based on multimedia remote image analysis

Bin Xu, Xiyuan Li, Hao Liang, Yuan Li
2019 EURASIP Journal on Image and Video Processing  
Based on this, this study analyzes the facial expression image and uses the wavelet transform algorithm to process the face image in complex lighting environment, thus improving the online transmission  ...  The experimental results show that the proposed method has a significant improvement in the correct rate compared with the traditional LBP feature classification method and can improve the theoretical  ...  Thereafter, the wavelet transform is used to process I^′ to obtain a low-frequency face image matrix LL i and a high-frequency face image matrix HL i , LH i , and HH i .  ... 
doi:10.1186/s13640-019-0437-4 fatcat:izr2cdzxtvddxazlv3cxruhg7a

Evolving Signal Processing for Brain–Computer Interfaces

S. Makeig, C. Kothe, T. Mullen, N. Bigdely-Shamlo, Zhilin Zhang, Kenneth Kreutz-Delgado
2012 Proceedings of the IEEE  
Here we discuss the current neuroscientific questions and data processing challenges facing BCI designers and outline some promising current and future directions to address them.  ...  | Because of the increasing portability and wearability of noninvasive electrophysiological systems that record and process electrical signals from the human brain, automated systems for assessing changes  ...  When applied to suitable data, sparse signal processing and modeling approaches can achieve dramatically better statistical power than methods that ignore sparsity, particularly when applied to sparse  ... 
doi:10.1109/jproc.2012.2185009 fatcat:ebed3ribeneptnatoxaoyzn4xm
« Previous Showing results 1 — 15 out of 6,409 results