Latent Dirichlet allocation (LDA) is useful in document analysis, image processing, and many information systems; however, its generalization performance has been left unknown because it is a singular learning machine to which regular statistical theory can not be applied. Stochastic matrix factorization (SMF) is a restricted matrix factorization in which matrix factors are stochastic; the column of the matrix is in a simplex. SMF is being applied to image recognition and text mining. We can understand SMF as a statistical model by which a stochastic matrix of given data is represented by a product of two stochastic matrices, whose generalization performance has also been left unknown because of non-regularity. In this paper, by using an algebraic and geometric method, we show the analytic equivalence of LDA and SMF, both of which have the same real log canonical threshold (RLCT), resulting in that they asymptotically have the same Bayesian generalization error and the same log marginal likelihood. Moreover, we derive the upper bound of the RLCT and prove that it is smaller than the dimension of the parameter divided by two, hence the Bayesian generalization errors of them are smaller than those of regular statistical models.
Latent Dirichlet Allocation (LDA) is a topic model widely used in natural language processing and machine learning. Most approaches to training the model rely on iterative algorithms, which makes it difficult to run LDA on big corpora that are best analyzed in parallel and distributed computational environments. Indeed, current approaches to parallel inference either don't converge to the correct posterior or require storage of large dense matrices in memory. We present a novel sampler that overcomes both problems, and we show that this sampler is faster, both empirically and theoretically, than previous Gibbs samplers for LDA. We do so by employing a novel P\'olya-urn-based approximation in the sparse partially collapsed sampler for LDA. We prove that the approximation error vanishes with data size, making our algorithm asymptotically exact, a property of importance for large-scale topic models. In addition, we show, via an explicit example, that - contrary to popular belief in the topic modeling literature - partially collapsed samplers can be more efficient than fully collapsed samplers. We conclude by comparing the performance of our algorithm with that of other approaches on well-known corpora.
Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In this paper, we first demystify the knowledge transfer mechanism behind multilingual topic models by defining an alternative but equivalent formulation. Based on this analysis, we then relax the assumption of training data required by most existing models, creating a model that only requires a dictionary for training. Experiments show that our new method effectively learns coherent multilingual topics from partially and fully incomparable corpora with limited amounts of dictionary resources.
We propose a new method of estimation in topic models, that is not a variation on the existing simplex finding algorithms, and that estimates the number of topics K from the observed data. We derive new finite sample minimax lower bounds for the estimation of A, as well as new upper bounds for our proposed estimator. We describe the scenarios where our estimator is minimax adaptive. Our finite sample analysis is valid for any number of documents (n), individual document length (N_i), dictionary size (p) and number of topics (K), and both p and K are allowed to increase with n, a situation not handled well by previous analyses. We complement our theoretical results with a detailed simulation study. We illustrate that the new algorithm is faster and more accurate than the current ones, although we start out with a computational and theoretical disadvantage of not knowing the correct number of topics K, while we provide the competing methods with the correct value in our simulations.
This paper aims at an aspect sentiment model for aspect-based sentiment analysis (ABSA) focused on micro reviews. This task is important in order to understand short reviews majority of the users write, while existing topic models are targeted for expert-level long reviews with sufficient co-occurrence patterns to observe. Current methods on aggregating micro reviews using metadata information may not be effective as well due to metadata absence, topical heterogeneity, and cold start problems. To this end, we propose a model called Micro Aspect Sentiment Model (MicroASM). MicroASM is based on the observation that short reviews 1) are viewed with sentiment-aspect word pairs as building blocks of information, and 2) can be clustered into larger reviews. When compared to the current state-of-the-art aspect sentiment models, experiments show that our model provides better performance on aspect-level tasks such as aspect term extraction and document-level tasks such as sentiment classification.
This work focuses on combining nonparametric topic models with Auto-Encoding Variational Bayes (AEVB). Specifically, we first propose iTM-VAE, where the topics are treated as trainable parameters and the document-specific topic proportions are obtained by a stick-breaking construction. The inference of iTM-VAE is modeled by neural networks such that it can be computed in a simple feed-forward manner. We also describe how to introduce a hyper-prior into iTM-VAE so as to model the uncertainty of the prior parameter. Actually, the hyper-prior technique is quite general and we show that it can be applied to other AEVB based models to alleviate the {\it collapse-to-prior} problem elegantly. Moreover, we also propose HiTM-VAE, where the document-specific topic distributions are generated in a hierarchical manner. HiTM-VAE is even more flexible and can generate topic distributions with better variability. Experimental results on 20News and Reuters RCV1-V2 datasets show that the proposed models outperform the state-of-the-art baselines significantly. The advantages of the hyper-prior technique and the hierarchical model construction are also confirmed by experiments.