%0 Journal Article %1 barbieri2013probabilistic %A Barbieri, Nicola %A Manco, Giuseppe %A Ritacco, Ettore %A Carnuccio, Marco %A Bevacqua, Antonio %D 2013 %I Springer US %J Machine Learning %K Gibbs lda markov models sampling topic %N 1 %P 5-29 %R 10.1007/s10994-013-5391-2 %T Probabilistic topic models for sequence data %U http://dx.doi.org/10.1007/s10994-013-5391-2 %V 93 %X Probabilistic topic models are widely used in different contexts to uncover the hidden structure in large text corpora. One of the main (and perhaps strong) assumption of these models is that generative process follows a bag-of-words assumption, i.e. each token is independent from the previous one. We extend the popular Latent Dirichlet Allocation model by exploiting three different conditional Markovian assumptions: (i) the token generation depends on the current topic and on the previous token; (ii) the topic associated with each observation depends on topic associated with the previous one; (iii) the token generation depends on the current and previous topic. For each of these modeling assumptions we present a

@article{barbieri2013probabilistic, abstract = {Probabilistic topic models are widely used in different contexts to uncover the hidden structure in large text corpora. One of the main (and perhaps strong) assumption of these models is that generative process follows a bag-of-words assumption, i.e. each token is independent from the previous one. We extend the popular Latent Dirichlet Allocation model by exploiting three different conditional Markovian assumptions: (i) the token generation depends on the current topic and on the previous token; (ii) the topic associated with each observation depends on topic associated with the previous one; (iii) the token generation depends on the current and previous topic. For each of these modeling assumptions we present a }, added-at = {2014-11-28T17:26:32.000+0100}, author = {Barbieri, Nicola and Manco, Giuseppe and Ritacco, Ettore and Carnuccio, Marco and Bevacqua, Antonio}, biburl = {https://www.bibsonomy.org/bibtex/291259bfa51c3bbd7856afa0b1d69e464/nosebrain}, description = {Probabilistic topic models for sequence data - Springer}, doi = {10.1007/s10994-013-5391-2}, interhash = {b6ee37d6caacbdb5ba85173284663d52}, intrahash = {91259bfa51c3bbd7856afa0b1d69e464}, issn = {0885-6125}, journal = {Machine Learning}, keywords = {Gibbs lda markov models sampling topic}, language = {English}, number = 1, pages = {5-29}, publisher = {Springer US}, timestamp = {2014-11-28T17:26:57.000+0100}, title = {Probabilistic topic models for sequence data}, url = {http://dx.doi.org/10.1007/s10994-013-5391-2}, volume = 93, year = 2013 }