Search

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). 1 Our data sets and code are available at: http://github.com/zengjichuan/Topic_Disc .

With the emergence of smartphones, Android has become a widely used mobile operating system. However, it is vulnerable when encountering various types of attacks. Every day, new malware threatens the security of users' devices and private data. Many methods have been proposed to classify malicious applications, utilizing static or dynamic analysis for classification. However, previous methods still suffer from unsatisfactory performance due to two challenges. First, they are unable to address the imbalanced data distribution problem, leading to poor performance for malware families with few members. Second, they are unable to address the zero-day malware (zero-day malware refers to malicious applications that exploit unknown vulnerabilities) classification problem. In this article, we introduce an innovative meta-learning approach for multi-family Android malware classification named Meta-MAMC, which uses meta-learning technology to learn meta-knowledge (i.e., the similarities and differences among different malware families) of few-family samples and combines new sampling algorithms to solve the above challenges. Meta-MAMC integrates (i) the meta-knowledge contained within the dataset to guide models in learning to identify unknown malware; and (ii) more accurate and diverse tasks based on novel sampling strategies, as well as directly adapting meta-learning to a new few-sample and zero-sample task to classify families. We have evaluated Meta-MAMC on two popular datasets and a corpus of real-world Android applications. The results demonstrate its efficacy in accurately classifying malicious applications belonging to certain malware families, even achieving 100% classification in some families. [ABSTRACT FROM AUTHOR]

Code search, which refers to the process of identifying the most relevant code snippets for a given natural language query, plays a crucial role in software maintenance. However, current approaches heavily rely on labeled data for training, which results in performance decreases when confronted with cross-domain scenarios including domain- or project-specific situations. This decline can be attributed to their limited ability to effectively capture the semantics associated with such scenarios. To tackle the aforementioned problem, we propose a zeRo-shot domAin adaPtion with pre-traIned moDels framework for code search named RAPID. The framework first generates synthetic data by pseudo labeling, then trains the CodeBERT with sampled synthetic data. To avoid the influence of noisy synthetic data and enhance the model performance, we propose a mixture sampling strategy to obtain hard negative samples during training. Specifically, the mixture sampling strategy considers both relevancy and diversity to select the data that are hard to be distinguished by the models. To validate the effectiveness of our approach in zero-shot settings, we conduct extensive experiments and find that RAPID outperforms the CoCoSoDa and UniXcoder model by an average of 15.7% and 10%, respectively, as measured by the MRR metric. When trained on full data, our approach results in an average improvement of 7.5% under the MRR metric using CodeBERT. We observe that as the model's performance in zero-shot tasks improves, the impact of hard negatives diminishes. Our observation also indicates that fine-tuning CodeT5 for generating pseudo labels can enhance the performance of the code search model, and using only 100-shot samples can yield comparable results to the supervised baseline. Furthermore, we evaluate the effectiveness of RAPID in real-world code search tasks in three GitHub projects through both human and automated assessments. Our findings reveal RAPID exhibits superior performance, e.g., an average improvement of 18% under the MRR metric over the top-performing model. [ABSTRACT FROM AUTHOR]

Technical Q&A sites, such as Stack Overflow and Ask Ubuntu, have been widely utilized by software engineers to seek support for development challenges. However, not all the raised questions get instant feedback, and the retrieved answers can vary in quality. The users can hardly avoid spending much time before solving their problems. Prior studies propose approaches to automatically recommend answers for the question posts on technical Q&A sites. However, the lengthiness and the lack of background knowledge issues limit the performance of answer recommendation on these sites. The irrelevant sentences in the posts may introduce noise to the semantics learning and prevent neural models from capturing the gist of texts. The lexical gap between question and answer posts further misleads current models to make failure recommendations. From this end, we propose a novel neural network named TopicAns for answer selection on technical Q&A sites. TopicAns aims at learning high-quality representations for the posts in Q&A sites with a neural topic model and a pre-trained model. This involves three main steps: (1) generating topic-aware representations of Q&A posts with the neural topic model, (2) incorporating the corpus-level knowledge from the neural topic model to enhance the deep representations generated by the pre-trained language model, and (3) determining the most suitable answer for a given query based on the topic-aware representation and the deep representation. Moreover, we propose a two-stage training technique to improve the stability of our model. We conduct comprehensive experiments on four benchmark datasets to verify our proposed TopicAns's effectiveness. Experiment results suggest that TopicAns consistently outperforms state-of-the-art techniques by over 30% in terms of Precision@1. [ABSTRACT FROM AUTHOR]

Mobile apps are becoming an integral part of people's daily life by providing various functionalities, such as messaging and gaming. App developers try their best to ensure user experience during app development and maintenance to improve the rating of their apps on app platforms and attract more user downloads. Previous studies indicated that responding to users' reviews tends to change their attitude towards the apps positively. Users who have been replied are more likely to update the given ratings. However, reading and responding to every user review is not an easy task for developers since it is common for popular apps to receive tons of reviews every day. Thus, automation tools for review replying are needed. To address the need above, the paper introduces a Transformer‐based approach, named TRRGen, to automatically generate responses to given user reviews. TRRGen extracts apps' categories, rating, and review text as the input features. By adapting a Transformer‐based model, TRRGen can generate appropriate replies for new reviews. Comprehensive experiments and analysis on the real‐world datasets indicate that the proposed approach can generate high‐quality replies for users' reviews and significantly outperform current state‐of‐art approaches on the task. The manual validation results on the generated replies further demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Water quality testing is of great significance for daily water use or water use in high precision manufacturing. The use of single-photon detection technology to detect water particles is one of the important methods of physical water quality detection. However, the current water quality particle detection technology needs to be improved in the range and accuracy of turbidity detection. The paper aims to use single-photon detection technology to design a fiber optic turbidity detection system to solve the current problems of small turbidity detection range and low accuracy in a large range. In response to this, this paper has made an in-depth understanding of single-photon detection technology and designed two sets of detection schemes using the performance of photons. The first set is the transmission optical fiber turbidity detection, which can effectively detect the ultralow turbidity range and a wide range of water quality particles. The second set is a scattering optical fiber turbidity detection system, which can effectively detect water particles in the low and medium turbidity range. In this paper, the two systems were integrated into a whole system, so the results of the two detection methods can also be compared, and the detected turbidity can be obtained more accurately. The experimental results showed that for the transmission optical fiber turbidity detection system, the detection effect of the system was the best under the incident light intensity of 11 wm, and the fitting value was 0.99; for the scattering optical fiber turbidity detection system, the detection effect of the system was the best under the incident light intensity of 4 wm, and the fitting value was 0.99. [ABSTRACT FROM AUTHOR]

This article takes advantage of the pilot Emissions Trading Scheme (ETS) project to estimate the causal impact of the ETS on CO2 abatement in China. The CO2 emissions and CO2 intensities of each province are calculated by using the fossil fuel data of 30 provincial administration regions from 2006 to 2016. Then difference in difference (DiD) models and propensity score matching (PSM) with panel data are applied to estimate the causal impact of the pilot ETS project. Results show that the pilot regions reduce their CO2 emissions and intensities more than the non-pilot regions under the pilot ETS project. The pilot ETS project significantly induced 12% decreases in the nominal CO2 intensity and 7.6% decrease in the real CO2 intensity, after controlling for regional heterogeneity, but its reduction effects on CO2 emissions are insignificant. Decreasing the proportion of coal to total energy consumption may be the main channel of the pilot ETS project inducing CO2 abatement. The estimated results for control variables indicate that upgrading industrial structures, attracting FDI, and purifying the export structure have significant effects on CO2 abatement. [ABSTRACT FROM AUTHOR]

Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail classes is the main challenge, which results in biased distribution estimation during training. Plenty of efforts have been devoted to ameliorating the challenge, including data resampling and synthesizing new training instances for tail classes. However, no prior research has exploited the transferable knowledge from head classes to tail classes for calibrating the distribution of tail classes. In this article, we suppose that tail classes can be enriched by similar head classes and propose a novel distribution calibration (DC) approach named as label-aware DC (LADC). LADC transfers the statistics from relevant head classes to infer the distribution of tail classes. Sampling from calibrated distribution further facilitates rebalancing the classifier. Experiments on both image and text long-tailed datasets demonstrate that LADC significantly outperforms existing methods. The visualization also shows that LADC provides a more accurate distribution estimation.

In order to investigate the effects of phenylalanine, tyrosine and tyramine on the growth of Lycoris radiata suspension cells and the accumulation of alkaloids, the growth quantity of the cells as well as the content of alkaloids in cells were determined, which were treated with above three kinds of precursors alone and phenylalanine combined with tyrosine respectively. The results indicate that the addition of phenylalanine alone and addition of phenylalanine on the basis of tyrosine at high concentration (200 micromol/L) had no significant effect on the growth of Lycoris radiata suspension cells and the content of alkaloids in cells; whereas tyrosine and tyramine promoted the growth of the cells and alkaloids accumulation. Treated with tyrosine at high concentration (200 micromol/L), the content of alkaloids of the cells was 2.56-fold higher than that of the control group, the amounts of lycoramine (3.77 mg/g) and galanthamine (4.46 mg/g) were 6.61-fold and 6.97-fold higher than that of the control group, respectively. When treated with tyramine (200 micromol/L), the amount of alkaloids in Lycoris radiata suspension cells was 2.63-fold higher than that of the control group, and the amounts of lycoramine (4.45 mg/g) and galanthamine (5.14 mg/g) were 9.08-fold and 9.18-fold higher than that of the control group, respectively. The above results demonstrate that adding tyrosine and tyramine in the media significantly promoted the growth of the Lycoris radiata suspension cells and alkaloids accumulation in the cells.

A high performance liquid chromatographic (HPLC) method was developed to determine the five endogenous hormones including indole-3-acetic acid (IAA), abscisic acid (ABA), gibberellic acid (GA3 ), zeatin (ZT) and salicylic acid (SA) in wheat. The separation conditions were optimized, and methanol was chosen as the extraction solvent. Then the extract was extracted by petroleum ether and ethyl acetate, and purified with the Sep-Pak C18 column. The chromatographic conditions were as follows: Eclipse XDB-C18 reversed phase column (250 mm x 4.6 mm, 5 microm), the flow rate of 1 mL/min, the injection volume of 10 microL, and the detection wavelength of 240 nm were used for the separation of SA from 14.5 min to 18 min, while the detection at 254 nm used for the separation of the others. Methanol (A) and acetic acid aqueous solution (pH 3.6) (B) were used as the mobile phases with the linear gradient set as follows: 0-7 min 20% A, 7-10 min 20% A-28% A, 10-17 min 28% A, 17-19 min 28% A-40% A, 19-35 min 40% A. The results showed that: the hormones were separated well with the recoveries of 96.9% - 98%, and the RSDs were in the range of 1.54% to 2.29%. It is a reliable method for rapid, accurate separation and determination of the endogenous hormones in wheat.