Filters








80,490 Hits in 4.5 sec

N-Poisson document modelling

Eugene L. Margulis
1992 Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '92  
We believe that further research in using the n-Poisson distribution to model full text document collections will help in developing a comprehensive and useful statistical model for such collections.  ...  Investigating the n-Poisson properties of non- English language document collections.  ... 
doi:10.1145/133160.133195 dblp:conf/sigir/Margulis92 fatcat:vjgglmmitnelzjhpaeoi6v6ghm

TSUNAMI THREAT EVALUATION BY HISTORICAL DOCUMENTS, NUMERICAL MODEL AND STOCHASTIC MODEL

Shigehisa Nakamura
1986 Coastal Engineering Proceedings  
An evaluation of local tsunami threat was studied first refering to the historical documents and the catalogs.  ...  Secondly, an example of a numerical model of a finite difference method was discussed in relation to problems for reproducing the past local tsunamis and predicting a forthcoming tsunami.  ...  using a stochastic model for an extended Poisson process.  ... 
doi:10.9753/icce.v20.194 fatcat:67u2to3lvralbga2c26acfr54a

Recurrent Coupled Topic Modeling over Sequential Documents [article]

Jinjin Guo, Longbing Cao, Zhiguo Gong
2021 arXiv   pre-print
The abundant sequential documents such as online archival, social media and news feeds are streamingly updated, where each chunk of documents is incorporated with smoothly evolving yet dependent topics  ...  A fully conjugate model is thus obtained to guarantee the effectiveness and efficiency of the inference technique.  ...  One of the benchmark models learning the evolution of topics is the state space model, in which the V -dimensional topic at step evolves via ∼ N ( −1 , Σ) [9] or the linear form ∼ N ( −1 , Σ) [47] .  ... 
arXiv:2106.13732v1 fatcat:hbfxszcnevgfplgnxiiqfnturm

Hierarchical Dirichlet model for document classification

Sriharsha Veeramachaneni, Diego Sona, Paolo Avesani
2005 Proceedings of the 22nd international conference on Machine learning - ICML '05  
documents into a given hierarchy.  ...  We present a novel and simple hierarchical Dirichlet generative model for text corpora and derive an efficient algorithm for the estimation of model parameters and the unsupervised classification of text  ...  We also note that for most generative models for document hierarchies the document length is assumed to be generated by a class-independent Poisson distribution.  ... 
doi:10.1145/1102351.1102468 dblp:conf/icml/VeeramachaneniSA05 fatcat:hbkemvqnevc4hjfuqi3pw2i2lu

Modèles de RI fondés sur l'information

Stéphane Clinchant, Eric Gaussier
2011 Document Numérique  
Nous introduisons ensuite une nouvelle famille de modèles probabilistes pour la RI, fondée sur la notion d'information.  ...  Lorsque la loi de probabilité sous-jacente est capable de modéliser le phénomène de rafale, alors le modèle devient naturellement valide au sens des contraintes heuristiques.  ...  Okapi, par exemple, suppose que les fréquences suivent un mélange de deux distributions de Poisson (2-Poisson), dans l'ensemble des documents pertinents et dans l'ensemble des documents non pertinents.  ... 
doi:10.3166/dn.14.2.103-123 fatcat:h7vwfgh54bgzthrt4p7cygoo4a

Medical documents classification using topic modeling

Maryam Nuser, Enas Al-Horani
2020 Indonesian Journal of Electrical Engineering and Computer Science  
LDA topic modeling technique is applied to classify these documents into the previous mentioned topics.  ...  Therefore, an automatic way to extract latent topics from these text documents is needed. Topic modeling is one of the techniques used to deal with this problem.  ...  LDA proposed the following generative process [8] for each document w in a corpus D: 1) Choose the number of words N according to Poisson distribution. 2) Then choose a topic mixture for the document  ... 
doi:10.11591/ijeecs.v17.i3.pp1524-1530 fatcat:xzml44lljbf3dmeytnftiaubma

Modeling error of \begin{document}$ \alpha $\end{document}-models of turbulence on a two-dimensional torus

Luigi C. Berselli, Università di Pisa, Dipartimento di Matematica, Via Buonarroti 1/c, I-56127 Pisa, Italy, Argus Adrian Dunca, Roger Lewandowski, Dinh Duong Nguyen, Department of Mathematics and Informatics, University Politehnica of Bucharest, Bucharest, Romania, IRMAR, UMR CNRS 6625, University of Rennes 1 and FLUMINANCE Team, INRIA, Rennes, France
2017 Discrete and continuous dynamical systems. Series B  
The turbulence models we study belong to the class of Large Eddy Simulation models (LES), used to carry out numerical simulations of turbulent flows, that cannot be performed by the Direct Numerical Simulations  ...  More specifically, we will consider the Leray-α, the simplified Bardina, and the modified Leray-α models.  ...  Once the velocity is calculated, the pressures p and p α are solutions of the following Poisson equations −∆p = ∇ · ((u · ∇)u) and − ∆p α = ∇ · (N (u α )).  ... 
doi:10.3934/dcdsb.2020305 fatcat:i6bmf6mjgre5tm3txh4ts7faka

A Stochastic Model for Simple Document Processing

Pierre MOUKELI MBINDZOUKOU, Institut Supérieur de Tectonolgie (IST), LAIMA – Institut Africain d'Informatique (IAI), Libreville – GABON, Arsène Roland MOUKOUKOU, Pr. David NACCACHE, Nino TSKHOVREBASHVILI
2019 International Journal of Information Technology and Computer Science  
Our simple document processing system derives from the general model described by MOUKELI and NEMBE.  ...  It is about an adaptation of the said general model to determine in terms of metrics and performance, its behavior in the particular case of simple document processing.  ...  Dynamic model of the system The dynamic model is used to describe the temporal behavior (evolution) of the system, which is modeled as N priority queues, and K document classes or document priority levels  ... 
doi:10.5815/ijitcs.2019.07.06 fatcat:7se2b43pbfgcllkidpuvffcbge

Gamma Process Poisson Factorization for Joint Modeling of Network and Documents [chapter]

Ayan Acharya, Dean Teffer, Jette Henderson, Marcus Tyler, Mingyuan Zhou, Joydeep Ghosh
2015 Lecture Notes in Computer Science  
This paper introduces Joint Gamma Process Poisson Factorization (J-GPPF) to jointly model network and side-information.  ...  Developing models to discover, analyze, and predict clusters within networked entities is an area of active and diverse research.  ...  For notational convenience, we represent the set of documents the n th author contributes to as Z n and the set of authors contributing to the d th document as Z d .  ... 
doi:10.1007/978-3-319-23528-8_18 fatcat:ohj5orawwnex3l4ct6gyukc474

Sparse Relational Topic Models for Document Networks [chapter]

Aonan Zhang, Jun Zhu, Bo Zhang
2013 Lecture Notes in Computer Science  
Previous work on relational topic models (RTM) has shown promise on learning latent topical representations for describing relational document networks and predicting pairwise links.  ...  Our model can also handle imbalance issues in real networks via introducing various cost parameters for positive and negative links.  ...  Graphical Model for SRTM considering only one document pair as an illustration ' d ' d n s ' d n w d dn s dn w .  ... 
doi:10.1007/978-3-642-40988-2_43 fatcat:h3xnk5l7abb3vi22lfbhylv7z4

Creating, documenting and sharing network models

Sharon M. Crook, James A. Bednar, Sandra Berger, Robert Cannon, Andrew P. Davison, Mikael Djurfeldt, Jochen Eppler, Birgit Kriener, Steve Furber, Bruce Graham, Hans E. Plesser, Lars Schwabe (+3 others)
2012 Network  
network model terminology, notation, and descriptions and explicit documentation of model scaling.  ...  However, methods for successfully documenting models for publication and for exchanging models and model components among these projects are still under development.  ...  description languages, which would aid modelers in effectively documenting models for publication and exchange.  ... 
doi:10.3109/0954898x.2012.722743 pmid:22994683 fatcat:oidvtvi5izfa7dbabjnre46rby

A Dual Embedding Space Model for Document Ranking [article]

Bhaskar Mitra, Eric Nalisnick, Nick Craswell, Rich Caruana
2016 arXiv   pre-print
We postulate that the proposed Dual Embedding Space Model (DESM) captures evidence on whether a document is about a query term in addition to what is modelled by traditional term-frequency based approaches  ...  We train a word2vec embedding model on a large unlabelled query corpus, but in contrast to how the model is commonly used, we retain both the input and the output projections, allowing us to leverage both  ...  For example, under the 2-Poisson model a document about Eminem will tend to mention the term 'eminem' repeatedly.  ... 
arXiv:1602.01137v1 fatcat:i6p7knyn3bdmfprli2f5cmdnze

A Statistical Model for Topically Segmented Documents [chapter]

Giovanni Ponti, Andrea Tagarelli, George Karypis
2011 Lecture Notes in Computer Science  
Experimental results have shown that, compared to existing generative models, our proposed model provides better perplexity of language modeling and better support for effective clustering of documents  ...  Generative models for text data are based on the idea that a document can be modeled as a mixture of topics, each of which is represented as a probability distribution over the terms.  ...  STM is based on a twoparameter Poisson Dirichlet process that employs a collapsed Gibbs sampler in a hierarchical model structure.  ... 
doi:10.1007/978-3-642-24477-3_21 fatcat:fbgyeihtd5c7vors6bjwwxhyz4

Two-way Poisson mixture models for simultaneous document classification and word clustering

Jia Li, Hongyuan Zha
2006 Computational Statistics & Data Analysis  
An approach to simultaneous document classification and word clustering is developed using a two-way mixture model of Poisson distributions.  ...  A mixture of Poisson distributions is used to model the multivariate distribution of the word counts in the documents within each class.  ...  Two-way mixtures of Poisson distributions We estimate the distribution of the document vector in each class using a parametric mixture model.  ... 
doi:10.1016/j.csda.2004.07.013 fatcat:os6mcafb2zchthcy7glrubjfge

Comparison of Generalized and Multilevel Poisson Regression Model with Poisson Model in Fertility Data in Rural of Fars Province (Iran)

N Zare,, M Sayadi, E Rezaeyan Fard,, H Ghaem, M Vosugh
2010 Majallah-i Dānishgāh-i ̒Ulūm-i Pizishkī-i Bābul  
If Poisson model is not applicable in a specific situation, it is better to apply generalized Poisson model and in cases that multilevel variable exists, it is better to use multilevel Poisson model.  ...  In cases that dependent variable is count, Poisson model is applied.  ...  This document was created with Win2PDF available at http://www.daneprairie.com. The unregistered version of Win2PDF is for evaluation or non-commercial use only.  ... 
doaj:5f8b1fdeaa7e4c00a55af66a8fa923cc fatcat:3kfvp67qjra4vhhxfxrvdqdeci
« Previous Showing results 1 — 15 out of 80,490 results