No abstract

Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics. * This work was mainly conducted when Jichuan Zeng was an intern in Tencent AI Lab. † Jing Li is the corresponding author. Training instances R1: [SuperBowl] I'll do anything to see the Steelers win. R2: [New.Music.Live] Please give wristbands, she have major Bieber Fever. Test instance S: [New.Music.Live] I will do anything for wristbands, gonna tweet till I win.

No abstract

Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app. For example, Hassan et al. found that responding to a review increases the chances of a user updating their given rating by up to six times compared to not responding. To alleviate the labor burden in replying to the bulk of user reviews, developers usually adopt a template-based strategy where the templates can express appreciation for using the app or mention the company email address for users to follow up. However, reading a large number of user reviews every day is not an easy task for developers. Thus, there is a need for more automation to help developers respond to user reviews.Addressing the aforementioned need, in this work we propose a novel approach RRGen that automatically generates review responses by learning knowledge relations between reviews and their responses. RRGen explicitly incorporates review attributes, such as user rating and review length, and learns the relations between reviews and corresponding responses in a supervised way from the available training data. Experiments on 58 apps and 309,246 review-response pairs highlight that RRGen outperforms the baselines by at least 67.4% in terms of BLEU-4 (an accuracy measure that is widely used to evaluate dialogue response generation systems). Qualitative analysis also confirms the effectiveness of RRGen in generating relevant and accurate responses.

With Android applications (apps) becoming increasingly popular, there exist huge risks lurking in the app marketplaces as most malicious software attempt to collect users' private information without their awareness. Although these apps request users' authorization for permissions, the users can still face privacy leakage issues due to their limited knowledge in distinguishing permissions. Thus, accurate and automatic permission checking is necessary and important for users' privacy protection. According to previous studies, analyzing app descriptions is a helpful way to examine whether some permissions are required for apps. Different from those studies, we consider app permissions from a more fine-grained perspective and aim at predicting the multiple correspondent permissions to one sentence of app description. In this paper, we propose an end-to-end framework for assessing the consistency between descriptions and permissions, named Assessing Consistency based on neural Network (AC-Net). For evaluation, a new dataset involving the description-to-permission correspondences of 1415 popular Android apps was built. The experiments demonstrate that AC-Net significantly outperforms the state-of-the-art method by over 24.5% in accurately predicting permissions from descriptions. INDEX TERMS Android security, app descriptions, app permissions, consistency assessment, text classification, deep learning.