We propose Adaptive Recursive Neural Network (AdaRNN) for target-dependent Twitter sentiment classification. AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them. It consists of more than one composition functions, and we model the adaptive sentiment propagations as distributions over these composition functions. The experimental studies illustrate that AdaRNN improves the baseline methods. Furthermore, we introduce a manually annotated dataset for target-dependent Twitter sentiment analysis.

Answering natural language questions over a knowledge base is an important and challenging task. Most of existing systems typically rely on hand-crafted features and rules to conduct question understanding and/or answer ranking. In this paper, we introduce multi-column convolutional neural networks (MCCNNs) to understand questions from three different aspects (namely, answer path, answer context, and answer type) and learn their distributed representations. Meanwhile, we jointly learn low-dimensional embeddings of entities and relations in the knowledge base. Question-answer pairs are used to train the model to rank candidate answers. We also leverage question paraphrases to train the column networks in a multi-task learning manner. We use FREEBASE as the knowledge base and conduct extensive experiments on the WEBQUESTIONS dataset. Experimental results show that our method achieves better or comparable performance compared with baseline systems. In addition, we develop a method to compute the salience scores of question words in different column networks. The results help us intuitively understand what MCCNNs learn.

Automatically generating product reviews is a meaningful, yet not well-studied task in sentiment analysis. Traditional natural language generation methods rely extensively on hand-crafted rules and predefined templates. This paper presents an attention-enhanced attribute-to-sequence model to generate product reviews for given attribute information, such as user, product, and rating. The attribute encoder learns to represent input attributes as vectors. Then, the sequence decoder generates reviews by conditioning its output on these vectors. We also introduce an attention mechanism to jointly generate reviews and align words with input attributes. The proposed model is trained end-to-end to maximize the likelihood of target product reviews given the attributes. We build a publicly available dataset for the review generation task by leveraging the Amazon book reviews and their metadata. Experiments on the dataset show that our approach outperforms baseline methods and the attention mechanism significantly improves the performance of our model.

In this paper we propose a new type of random CSP model, called Model RB, which is a revision to the standard Model B. It is proved that phase transitions from a region where almost all problems are satisfiable to a region where almost all problems are unsatisfiable do exist for Model RB as the number of variables approaches infinity. Moreover, the critical values at which the phase transitions occur are also known exactly. By relating the hardness of Model RB to Model B, it is shown that there exist a lot of hard instances in Model RB.

As a significant factor in urban planning, traffic forecasting and prediction of epidemics, modeling patterns of human mobility draws intensive attention from researchers for decades. Power-law distribution and its variations are observed from quite a few real-world human mobility datasets such as the movements of banking notes, trackings of cell phone users' locations and trajectories of vehicles. In this paper, we build models for 20 million trajectories with fine granularity collected from more than 10 thousand taxis in Beijing. In contrast to most models observed in human mobility data, the taxis' traveling displacements in urban areas tend to follow an exponential distribution instead of a power-law. Similarly, the elapsed time can also be well approximated by an exponential distribution. Worth mentioning, analysis of the interevent time indicates the bursty nature of human mobility, similar to many other human activities.