We consider the problem of naming objects in complex, natural scenes containing widely varying object appearance and subtly different names. Informed by cognitive research, we propose an approach based on sharing context based object hypotheses between visual and lexical spaces. To this end, we present the Visual Semantic Integration Model (VSIM) that represents object labels as entities shared between semantic and visual contexts and infers a new image by updating labels through context switching. At the core of VSIM is a semantic Pachinko Allocation Model and a visual nearest neighbor Latent Dirichlet Allocation Model. For inference, we derive an iterative Data Augmentation algorithm that pools the label probabilities and maximizes the joint label posterior of an image. Our model surpasses the performance of state-of-art methods in several visual tasks on the challenging SUN09 dataset.

Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified given observable moments of a certain order. We consider probabilistic admixture or topic models in the overcomplete regime, where the number of latent topics can greatly exceed the size of the observed word vocabulary. While general overcomplete topic models are not identifiable, we establish generic identifiability under a constraint, referred to as topic persistence. Our sufficient conditions for identifiability involve a novel set of "higher order" expansion conditions on the topic-word matrix or the population structure of the model. This set of higher-order expansion conditions allow for overcomplete models, and require the existence of a perfect matching from latent topics to higher order observed words. We establish that random structured topic models are identifiable w.h.p. in the overcomplete regime. Our identifiability results allows for general (non-degenerate) distributions for modeling the topic proportions, and thus, we can handle arbitrarily correlated topics in our framework. Our identifiability results imply uniqueness of a class of tensor decompositions with structured sparsity which is contained in the class of Tucker decompositions, but is more general than the Candecomp/Parafac (CP) decomposition.

Due to the explosive growth of the Internet online reviews, we can easily collect a large amount of labeled reviews from different domains. But only some of them are beneficial for training a desired target-domain sentiment classifier. Therefore, it is important for us to identify those samples that are the most relevant to the target domain and use them as training data. To address this problem, a novel approach, based on instance selection and instance weighting via PU learning, is proposed. PU learning is used at first to learn an in-target-domain selector, which assigns an in-target-domain probability to each sample in the training set. For instance selection, the samples with higher in-target-domain probability are used as training data; For instance weighting, the calibrated in-target-domain probabilities are used as sampling weights for training an instance-weighted naive Bayes model, based on the principle of maximum weighted likelihood estimation. The experimental results prove the necessity and effectiveness of the approach, especially when the size of training data is large. It is also proved that the larger the Kullback-Leibler divergence between the training and test data is, the more effective the proposed approach will be.

Hashtags can be viewed as an indication to the context of the tweet or as the core idea expressed in the tweet. They provide valuable information for many applications, such as information retrieval, opinion mining, text classification, and so on. However, only a small number of microblogs are manually tagged. To address this problem, in this work, we propose a topical translation model for microblog hashtag suggestion. We assume that the content and hashtags of the tweet are talking about the same themes but written in different languages. Under the assumption, hashtag suggestion is modeled as a translation process from content to hashtags. Moreover, in order to cover the topic of tweets, the proposed model regards the translation probability to be topic-specific. It uses topic-specific word trigger to bridge the vocabulary gap between the words in tweets and hashtags, and discovers the topics of tweets by a topic model designed for microblogs. Experimental results on the dataset crawled from real world microblogging service demonstrate that the proposed method outperforms state-of-the-art methods.

Relational topic models have shown promise on analyzing document network structures and discovering latent topic representations. This paper presents three extensions: 1) unlike the common link likelihood with a diagonal weight matrix that allows the-same-topic interactions only, we generalize it to use a full weight matrix that captures all pairwise topic interactions and is applicable to asymmetric networks; 2) instead of doing standard Bayesian inference, we perform regularized Bayesian inference with a regularization parameter to deal with the imbalanced link structure issue in common real networks; and 3) instead of doing variational approximation with strict mean-field assumptions, we present a collapsed Gibbs sampling algorithm for the generalized relational topic models without making restricting assumptions. Experimental results demonstrate the significance of these extensions on improving the prediction performance, and the time efficiency can be dramatically improved with a simple fast approximation method.

In the last decade, latent Dirichlet allocation (LDA) successfully discovers the statistical distribution of the topics over a unstructured text corpus. Meanwhile, more and more document data come up with rich human-provided tag information during the evolution of the Internet, which called semi- structured data. The semi-structured data contain both unstructured data (e.g., plain text) and metadata, such as papers with authors and web pages with tags. In general, different tags in a document play different roles with their own weights. To model such semi-structured documents is non-trivial. In this paper, we propose a novel method to model tagged documents by a topic model, called Tag-Weighted Topic Model (TWTM). TWTM is a framework that leverages the tags in each document to infer the topic components for the documents. This allows not only to learn document-topic distributions, but also to infer the tag-topic distributions for text mining (e.g., classification, clustering, and recommendations). Moreover, TWTM automatically infers the probabilistic weights of tags for each document. We present an efficient variational inference method with an EM algorithm for estimating the model parameters. The experimental results show that our TWTM approach outperforms the baseline algorithms over three corpora in document modeling and text classification.

In traditional topic models such as LDA, a word is generated by choosing a topic from a collection. However, existing topic models do not identify different types of topics in a document, such as topics that represent the content and topics that represent the sentiment. In this paper, our goal is to discover such different types of topics, if they exist. We represent our model as several parallel topic models (called topic factors), where each word is generated from topics from these factors jointly. Since the latent membership of the word is now a vector, the learning algorithms become challenging. We show that using a variational approximation still allows us to keep the algorithm tractable. Our experiments over several datasets show that our approach consistently outperforms many classic topic models while also discovering fewer, more meaningful, topics.

In the literature, various approaches have been proposedto address the domain adaptation problem in sentiment classification (also called cross-domainsentiment classification). However, the adaptation performance normally much suffers when the data distributionsin the source and target domains differ significantly. In this paper, we suggest to perform activelearning for cross-domain sentiment classification by actively selecting a smallamount of labeled data in the target domain. Accordingly, we propose an novel activelearning approach for cross-domain sentiment classification. First, we traintwo individual classifiers, i.e., the source and target classifiers with thelabeled data from the source and target respectively. Then, the two classifiersare employed to select informative samples with the selection strategy of QueryBy Committee (QBC). Third, the two classifier is combined to make theclassification decision. Importantly, the two classifiers are trained by fullyexploiting the unlabeled data in the target domain with the label propagation(LP) algorithm. Empirical studies demonstrate the effectiveness of our active learning approach for cross-domainsentiment classification over some strong baselines.

Cross lingual entity linking means linking an entity mention in a background source document in one language with the corresponding real world entity in a knowledge base written in the other language. The key problem is to measure the similarity score between the context of the entity mention and the document of the candidate entity. This paper presents a general framework for doing cross lingual entity linking by leveraging a large scale and bilingual knowledge base, Wikipedia. We introduce a bilingual topic model that mining bilingual topic from this knowledge base with the assumption that the same Wikipedia concept documents of two different languages share the same semantic topic distribution. The extracted topics have two types of representation, with each type corresponding to one language. Thus both the context of the entity mention and the document of the candidate entity can be represented in a space using the same semantic topics. We use these topics to do cross lingual entity linking. Experimental results show that the proposed approach can obtain the competitive results compared with the state-of-art approach.

Topic models have been widely used to identify topics in text corpora. It is also known that purely unsupervised models often result in topics that are not comprehensible in applications. In recent years, a number of knowledge-based models have been proposed, which allow the user to input prior knowledge of the domain to produce more coherent and meaningful topics. In this paper, we go one step further to study how the prior knowledge from other domains can be exploited to help topic modeling in the new domain. This problem setting is important from both the application and the learning perspectives because knowledge is inherently accumulative. We human beings gain knowledge gradually and use the old knowledge to help solve new problems. To achieve this objective, existing models have some major difficulties. In this paper, we propose a novel knowledge-based model, called MDK-LDA, which is capable of using prior knowledge from multiple domains. Our evaluation results will demonstrate its effectiveness.