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.
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.
Commit messages record code changes (e.g., feature modifications and bug repairs) in natural language, and are useful for program comprehension. Due to the frequent updates of software and time cost, developers are generally unmotivated to write commit messages for code changes. Therefore, automating the message writing process is necessitated. Previous studies on commit message generation have been benefited from generation models or retrieval models, but code structure of changed code, which can be important for capturing code semantics, has not been explicitly involved. Moreover, although generation models have the advantages of synthesizing commit messages for new code changes, they are not easy to bridge the semantic gap between code and natural languages which could be mitigated by retrieval models. In this paper, we propose a novel commit message generation model, named ATOM, which explicitly incorporates abstract syntax tree for representing code changes and integrates both retrieved and generated messages through hybrid ranking. Specifically, the hybrid ranking module can prioritize the most accurate message from both retrieved and generated messages regarding one code change. We evaluate the proposed model ATOM on our dataset crawled from 56 popular Java repositories. Experimental results demonstrate that ATOM increases the state-of-the-art models by 30.72% in terms of BLEU-4 (an accuracy measure that is widely used to evaluate text generation systems). Qualitative analysis also demonstrates the effectiveness of ATOM in generating accurate code commit messages.
This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discover word clusters indicating what a conversation concerns (i.e., topics) and those reflecting how participants voice their opinions (i.e., discourse).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.