unread-papers-13.12.2019.json

{"Title":"Establishing Benchmarks For Learning Program Representations","URL":"http://ceur-ws.org/Vol-2510/sattose2019_paper_14.pdf","Abstract":{"FirstLine":"Recent advances in the field of machine learning have shown great promise in solving","Rest":"various software engineering tasks. However, unlike machine learning techniques used in fields such as NLP (Natural Language Processing) where text …"}}
{"Title":"Adopting Program Synthesis for Test Amplification","URL":"https://www.researchgate.net/profile/Mehrdad_Abdi2/publication/337709673_Adopting_Program_Synthesis_for_Test_Amplification/links/5de65be6299bf10bc33bac44/Adopting-Program-Synthesis-for-Test-Amplification.pdf","Abstract":{"FirstLine":"Program synthesis is the task of enabling a computer system to automatically write","Rest":"program code based on user intent. Test amplification on the other hand is an emerging research area, where the goal is to generate new test cases from manually …"}}
{"Title":"Evaluating Semantic Representations of Source Code","URL":"https://arxiv.org/pdf/1910.05177","Abstract":{"FirstLine":"Learned representations of source code enable various software developer tools, eg, to","Rest":"detect bugs or to predict program properties. At the core of code representations often are word embeddings of identifier names in source code, because identifiers …"}}
{"Title":"Learning to Fuzz from Symbolic Execution with Application to Smart Contracts","URL":"https://files.sri.inf.ethz.ch/website/papers/ccs19-ilf.pdf","Abstract":{"FirstLine":"Fuzzing and symbolic execution are two complementary techniques for discovering software","Rest":"vulnerabilities. Fuzzing is fast and scalable, but can be ineffective when it fails to randomly select the right inputs. Symbolic execution is thorough but slow and …"}}
{"Title":"ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking","URL":"https://arxiv.org/pdf/1912.02972","Abstract":{"FirstLine":"Commit messages record code changes (eg, feature modifications and bug repairs) in","Rest":"natural language, and are useful for program comprehension. Due to the frequent updates of software and time cost, developers are generally unmotivated to write …"}}
{"Title":"Improving Bug Detection via Context-Based Code Representation Learning and Attention-Based Neural Networks","URL":"https://web.njit.edu/~davidsw/papers/oopsla19_id_201.pdf","Abstract":{"FirstLine":"• Rule-based bug detection. In this type of approaches, several programming rules are","Rest":"predefined to statically detect common programming flaws or defects. A popular example of this type of approaches is FindBugs [Hovemeyer and Pugh 2007]. While …"}}
{"Title":"Generating precise error specifications for C: a zero shot learning approach","URL":"https://dl.acm.org/ft_gateway.cfm?id=3360586\u0026type=pdf","Abstract":{"FirstLine":"In C programs, error specifications, which specify the value range that each function","Rest":"returns to indicate failures, are widely used to check and propagate errors for the sake of reliability and security. Various kinds of C analyzers employ error …"}}
{"Title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","URL":"https://arxiv.org/pdf/1909.09436","Abstract":{"FirstLine":"Semantic code search is the task of retrieving relevant code given a natural language","Rest":"query. While related to other information retrieval tasks, it requires bridging the gap between the language used in code (often abbreviated and highly technical) …"}}
{"Title":"Using Distributed Representation of Code for Bug Detection","URL":"https://arxiv.org/pdf/1911.12863","Abstract":{"FirstLine":"Recent advances in neural modeling for bug detection have been very promising. More","Rest":"specifically, using snippets of code to create continuous vectors or\\textit {embeddings} has been shown to be very good at method name prediction and …"}}
{"Title":"N-Grams as a Measure of Naturalness and Complexity","URL":"http://www.diva-portal.org/smash/get/diva2:1369387/FULLTEXT01.pdf","Abstract":{"FirstLine":"We live in a time where software is used everywhere. It is used even for creating other","Rest":"software by helping developers with writing or generating new code. To do this properly, metrics to measure software quality are being used to evaluate the final …"}}
{"Title":"Commit2Vec: Learning Distributed Representations of Code Changes","URL":"https://arxiv.org/pdf/1911.07605","Abstract":{"FirstLine":"Deep learning methods, which have found successful applications in fields like image","Rest":"classification and natural language processing, have recently been applied to source code analysis too, due to the enormous amount of freely available source …"}}
{"Title":"A machine learning based automatic folding of dynamically typed languages","URL":"https://dl.acm.org/citation.cfm?id=3342746","Abstract":{"FirstLine":"The popularity of dynamically typed languages has been growing strongly lately. Elegant","Rest":"syntax of such languages like javascript, python, PHP and ruby pays back when it comes to finding bugs in large codebases. The analysis is hindered by …"}}
{"Title":"Improve Language Modelling for Code Completion through Statement Level Language Model based on Statement Embedding Generated by BiLSTM","URL":"https://arxiv.org/pdf/1909.11503","Abstract":{"FirstLine":"Language models such as RNN, LSTM or other variants have been widely used as generative","Rest":"models in natural language processing. In last few years, taking source code as natural languages, parsing source code into a token sequence and using a …"}}
{"Title":"MACHINE LEARNING FOR CODE SYNTHESIS AND ANALYSIS","URL":"https://www.cs.colostate.edu/~steveko/wp/projects/KommruschResearchExam.pdf","Abstract":{"FirstLine":"Deep learning has been successfully applied to a wide array of problems due to its","Rest":"versatility and the variety of algorithms being developed. Deep learning for natural language processing makes use of recurrent networks, attention layers, copy …"}}
{"Title":"Relational Verification using Reinforcement Learning","URL":"https://www.cs.utexas.edu/~isil/oopsla19.pdf","Abstract":{"FirstLine":"Authors' addresses: Jia Chen, Department of Computer Science, University of Texas at","Rest":"Austin, Austin, Texas, 78712-0233, USA, jchen@ cs. utexas. edu; Jiayi Wei, Department of Computer Science, University of Texas at Austin, Austin, Texas, 78712 …"}}
{"Title":"Modeling Security Weaknesses to Enable Practical Run-time Defenses","URL":"https://kilthub.cmu.edu/ndownloader/files/17435732","Abstract":{"FirstLine":"Security weaknesses are sometimes caused by patterns in human behaviors. However, it can","Rest":"be difficult to identify such patterns in a practical, yet accurate way. In order to fix security weaknesses, it is crucial to identify them. Useful systems to …"}}
{"Title":"Encodings for Enumeration-Based Program Synthesis","URL":"https://link.springer.com/chapter/10.1007/978-3-030-30048-7_34","Abstract":{"FirstLine":"Program synthesis is the problem of finding a program that satisfies a given","Rest":"specification. Most program synthesizers are based on enumerating program candidates that satisfy the specification. Recently, several new tools for program …"}}
{"Title":"Code Summarization with Abstract Syntax Tree","URL":"https://link.springer.com/chapter/10.1007/978-3-030-36802-9_69","Abstract":{"FirstLine":"Code summarization, which provides a high-level description of the function implemented","Rest":"by code, plays a vital role in software maintenance and code retrieval. Traditional approaches focus on retrieving similar code snippets to generate …"}}
{"Title":"Structural Language Models for Any-Code Generation","URL":"https://arxiv.org/pdf/1910.00577","Abstract":{"FirstLine":"We address the problem of Any-Code Generation (AnyGen)-generating code without any","Rest":"restriction on the vocabulary or structure. The state-of-the-art in this problem is the sequence-to-sequence (seq2seq) approach, which treats code as a sequence …"}}
{"Title":"Do People Prefer\" Natural\" code?","URL":"https://arxiv.org/pdf/1910.03704","Abstract":{"FirstLine":"Natural code is known to be very repetitive (much more so than natural language corpora);","Rest":"furthermore, this repetitiveness persists, even after accounting for the simpler syntax of code. However, programming languages are very expressive …"}}
{"Title":"AutoPandas: Neural-Backed Generators for Program Synthesis","URL":"https://people.eecs.berkeley.edu/~ksen/papers/autopandas2.pdf","Abstract":{"FirstLine":"Developers nowadays have to contend with a growing number of APIs. Many of these APIs are","Rest":"very useful to developers, increasing the ease of code re-use. API functions provide implementations of functionalities that are often more efficient …"}}
{"Title":"Generating Commit Messages from Git Diffs","URL":"https://arxiv.org/pdf/1911.11690","Abstract":{"FirstLine":"Commit messages aid developers in their understanding of a continuously evolving","Rest":"codebase. However, developers not always document code changes properly. Automatically generating commit messages would relieve this burden on developers …"}}
{"Title":"Learning Lenient Parsing \u0026 Typing via Indirect Supervision","URL":"https://arxiv.org/pdf/1910.05879","Abstract":{"FirstLine":"Both professional coders and teachers frequently deal with imperfect (fragmentary,","Rest":"incomplete, ill-formed) code. Such fragments are common in StackOverflow; students also frequently produce ill-formed code, for which instructors, TAs (or students …"}}
{"Title":"Code Generation from Supervised Code Embeddings","URL":"https://link.springer.com/chapter/10.1007/978-3-030-36808-1_42","Abstract":{"FirstLine":"Code generation, which generates source code from natural language, is beneficial for","Rest":"constructing smarter I ntegrated D evelopment E nvironments (IDEs), retrieving code more effectively and so on. Traditional approaches are based on matching …"}}
{"Title":"Перспективы применения нейронных сетей в суперкомпиляции и насыщении равенствами","URL":"https://keldysh.ru/abrau/2019/theses/35.pdf","Abstract":{"FirstLine":"Многие методы преобразования программ (включая суперкомпиляцию и насыщение равенствами)","Rest":"можно сформулировать в виде набора правил переписывания графов или термов, применяемых в некотором порядке …"}}
{"Title":"On Herb Compatibility Rule of Insomnia Based on Machine Learning Approaches","URL":"https://www.researchgate.net/profile/Fang_Hu6/publication/337157715_On_Herb_Compatibility_Rule_of_Insomnia_Based_on_Machine_Learning_Approaches/links/5dc8cd58458515143500741d/On-Herb-Compatibility-Rule-of-Insomnia-Based-on-Machine-Learning-Approaches.pdf","Abstract":{"FirstLine":"Recent research in machine learning has led to significant progress in various research","Rest":"fields. Especially, the knowledge discovery using this method in Traditional Chinese Medicine (TCM) has been becoming a hot topic. In this paper, we studied …"}}
{"Title":"Twin-Finder: Integrated Reasoning Engine for Pointer-related Code Clone Detection","URL":"https://arxiv.org/pdf/1911.00561","Abstract":{"FirstLine":"Detecting code clones is crucial in various software engineering tasks. In particular,","Rest":"code clone detection can have significant uses in the context of analyzing and fixing bugs in large scale applications. However, prior works, such as machine learning …"}}
{"Title":"Assessing the Generalizability of code2vec Token Embeddings","URL":"http://www.mysmu.edu/faculty/davidlo/papers/ase19-code2vec.pdf","Abstract":{"FirstLine":"Many Natural Language Processing (NLP) tasks, such as sentiment analysis or syntactic","Rest":"parsing, have benefited from the development of word embedding models. In particular, regardless of the training algorithms, the learned embeddings have …"}}
{"Title":"Class Name Recommendation based on Graph Embedding of Program Elements","URL":"https://kuri8ive.github.io/preprints/apsec2019.pdf","Abstract":{"FirstLine":"In software development, the quality of identifier names is important because it greatly","Rest":"affects program comprehension for developers. However, naming identifiers that appropriately represent the nature or behavior of program elements such as …"}}
{"Title":"Universal Approximation with Certified Networks","URL":"https://arxiv.org/pdf/1909.13846","Abstract":{"FirstLine":"Training neural networks to be certifiably robust is a powerful defense against","Rest":"adversarial attacks. However, while promising, state-of-the-art results with certified training are far from satisfactory. Currently, it is very difficult to train a neural network …"}}
{"Title":"Evaluating Lexical Approximation of Program Dependence","URL":"https://www.sciencedirect.com/science/article/pii/S016412121930233X","Abstract":{"FirstLine":"Complex dependence analysis typically provides an underpinning approximation of true","Rest":"program dependence. We investigate the effectiveness of using lexical information to approximate such dependence, introducing two new deletion …"}}
{"Title":"On The Quality of Identifiers in Test Code","URL":"https://www.inf.usi.ch/phd/lin/downloads/Lin2019c.pdf","Abstract":{"FirstLine":"Meaningful, expressive identifiers in source code can enhance the readability and reduce","Rest":"comprehension efforts. Over the past years, researchers have devoted considerable effort to understanding and improving the naming quality of identifiers …"}}
{"Title":"Software Vulnerability Discovery via Learning Multi-domain Knowledge Bases","URL":"https://ieeexplore.ieee.org/abstract/document/8906156/","Abstract":{"FirstLine":"Machine learning (ML) has great potential in automated code vulnerability discovery.","Rest":"However, automated discovery application driven by off-the-shelf machine learning tools often performs poorly due to the shortage of high-quality training data. The …"}}
{"Title":"Learning based Methods for Code Runtime Complexity Prediction","URL":"https://arxiv.org/pdf/1911.01155","Abstract":{"FirstLine":"Predicting the runtime complexity of a programming code is an arduous task. In fact, even","Rest":"for humans, it requires a subtle analysis and comprehensive knowledge of algorithms to predict time complexity with high fidelity, given any code. As per …"}}
{"Title":"DeepVS: An Efficient and Generic Approach for Source Code Modeling Usage","URL":"https://arxiv.org/pdf/1910.06500","Abstract":{"FirstLine":"Recently deep learning-based approaches have shown great potential in the modeling of","Rest":"source code for various software engineering tasks. These techniques lack adequate generalization and resistance to acclimate the use of such models in a …"}}
{"Title":"Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits","URL":"https://arxiv.org/pdf/1911.07620","Abstract":{"FirstLine":"Public vulnerability databases such as CVE and NVD account for only 60% of security","Rest":"vulnerabilities present in open-source projects, and are known to suffer from inconsistent quality. Over the last two years, there has been considerable growth in …"}}
{"Title":"Personalized Code Recommendation","URL":"https://ieeexplore.ieee.org/abstract/document/8919008/","Abstract":{"FirstLine":"The current state-of-the-art methods in code recommendation mostly take the crowd-based","Rest":"approach. The basic idea is to collect and extract code patterns from a large pool of available source code and use those code patterns for recommendations …"}}
{"Title":"Linguistic Change in Open Source Software","URL":"https://ieeexplore.ieee.org/abstract/document/8918934/","Abstract":{"FirstLine":"In this paper, we seek to advance the state-of-the-art in code evolution analysis","Rest":"research and practice by statistically analyzing, interpreting, and formally describing the evolution of code lexicon in Open Source Software (OSS). The underlying …"}}
{"Title":"zkay: Specifying and Enforcing Data Privacy in Smart Contracts","URL":"https://files.sri.inf.ethz.ch/website/papers/ccs19-zkay.pdf","Abstract":{"FirstLine":"Privacy concerns of smart contracts are a major roadblock preventing their wider","Rest":"adoption. A promising approach to protect private data is hiding it with cryptographic primitives and then enforcing correctness of state updates by Non-Interactive Zero …"}}
{"Title":"Neural Program Synthesis By Self-Learning","URL":"https://arxiv.org/pdf/1910.05865","Abstract":{"FirstLine":"Neural inductive program synthesis is a task generating instructions that can produce","Rest":"desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the …"}}
{"Title":"A Deep Learning Model for Source Code Generation","URL":"http://docs.udc.edu/seas/Faculty/Oladunni-A-Deep-Learning-Model-for-Source-Code-Generation.pdf","Abstract":{"FirstLine":"ABSTRACT Natural Language Processing (NLP) models have been used extensively to study","Rest":"relationship among words in a corpus. Inspired by models such as n-gram we developed a model for analyzing source code via its Abstract Syntax …"}}
{"Title":"Using Sequence-to-Sequence Learning for Repairing C Vulnerabilities","URL":"https://arxiv.org/pdf/1912.02015","Abstract":{"FirstLine":"Software vulnerabilities affect all businesses and research is being done to avoid,","Rest":"detect or repair them. In this article, we contribute a new technique for automatic vulnerability fixing. We present a system that uses the rich software development …"}}
{"Title":"Poster: Finding JavaScript Name Conflicts on the Web","URL":"https://dl.acm.org/citation.cfm?id=3363268","Abstract":{"FirstLine":"Including JavaScript code from many different hosts is a popular practice in developing","Rest":"web applications. For example, to include a social plugin like the Facebook Like button, a web developer needs to only include a script from facebook …"}}
{"Title":"Deep Transfer Learning for Source Code Modeling","URL":"https://arxiv.org/pdf/1910.05493","Abstract":{"FirstLine":"In recent years, deep learning models have shown great potential in source code modeling","Rest":"and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they …"}}
{"Title":"Intelligent Software Engineering in the Context of Agile Software Development: a Systematic Literature Review","URL":"https://www.sciencedirect.com/science/article/pii/S0950584919302587","Abstract":{"FirstLine":"Abstract CONTEXT: Intelligent Software Engineering (ISE) refers to the application of","Rest":"intelligent techniques to software engineering. We define an “intelligent technique” as a technique that explores data (from digital artifacts or domain experts) for …"}}
{"Title":"Imitation-Projected Programmatic Reinforcement Learning","URL":"https://deeplearn.org/arxiv/99210/imitation-projected-programmatic-reinforcement-learning","Abstract":{"FirstLine":"We study the problem of programmatic reinforcement learning, in which policies are","Rest":"represented as short programs in a symbolic language. Such programmatic policies can be more interpretable, generalizable, and amenable to formal verification than …"}}
{"Title":"Testing Neural Program Analyzers","URL":"https://www.researchgate.net/profile/Mohammad_Alipour9/publication/336220651_Testing_Neural_Program_Analyzers/links/5d94dadb458515c1d38ecdc4/Testing-Neural-Program-Analyzers.pdf","Abstract":{"FirstLine":"Deep neural networks have been increasingly used in software engineering and program","Rest":"analysis tasks. They usually take a program and make some predictions about it, eg, bug prediction. We call these models neural program analyzers. The …"}}
{"Title":"Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks","URL":"https://arxiv.org/pdf/1910.00942","Abstract":{"FirstLine":"Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful","Rest":"node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE and most of their …"}}
{"Title":"Improving Textual Network Learning with Variational Homophilic Embeddings","URL":"https://arxiv.org/pdf/1909.13456","Abstract":{"FirstLine":"The performance of many network learning applications crucially hinges on the success of","Rest":"network embedding algorithms, which aim to encode rich network information into low-dimensional vertex-based vector representations. This paper …"}}
{"Title":"Translationese as a Language in\" Multilingual\" NMT","URL":"https://arxiv.org/pdf/1911.03823","Abstract":{"FirstLine":"Machine translation has an undesirable propensity to produce\" translationese\" artifacts,","Rest":"which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (ie natural) text as …"}}
{"Title":"Towards a Model to Appraise and Suggest Identifier Names","URL":"https://ieeexplore.ieee.org/abstract/document/8918988/","Abstract":{"FirstLine":"Unknowingly, identifiers in the source code of a software system play a vital role in","Rest":"determining the quality of the system. Ambiguous and confusing identifier names lead developers to not only misunderstand the behavior of the code but also …"}}
{"Title":"Reducing Features to Improve Link Prediction Performance in Location Based Social Networks, Non-Monotonically Selected Subset from Feature Clusters","URL":"https://asonamdata.com/ASONAM2019_Proceedings/pdf/papers/139_0809_064.pdf","Abstract":{"FirstLine":"In most cases, feature sets available for machine learning algorithms require a feature","Rest":"engineering approach to pick the subset for optimal performance. During our link prediction research, we had observed the same challenge for features of …"}}
{"Title":"Recognizing lines of code violating company-specific coding guidelines using machine learning","URL":"https://link.springer.com/article/10.1007/s10664-019-09769-8","Abstract":{"FirstLine":"Software developers in big and medium-size companies are working with millions of lines","Rest":"of code in their codebases. Assuring the quality of this code has shifted from simple defect management to proactive assurance of internal code quality. Although …"}}
{"Title":"On the use of supervised machine learning for assessing schedulability: application to Ethernet TSN","URL":"https://dl.acm.org/citation.cfm?id=3356409","Abstract":{"FirstLine":"In this work, we ask if Machine Learning (ML) can provide a viable alternative to","Rest":"conventional schedulability analysis to determine whether a real-time Ethernet network meets a set of timing constraints. Otherwise said, can an algorithm learn …"}}
{"Title":"Code Generation as a Dual Task of Code Summarization","URL":"https://arxiv.org/pdf/1910.05923","Abstract":{"FirstLine":"Code summarization (CS) and code generation (CG) are two crucial tasks in the field of","Rest":"automatic software development. Various neural network-based approaches are proposed to solve these two tasks separately. However, there exists a specific …"}}
{"Title":"Why do they ask? An exploratory study of crowd discussions about Android application programming interface in stack overflow","URL":"https://link.springer.com/article/10.1007/s11771-019-4185-5","Abstract":{"FirstLine":"Nowadays, more and more Android developers prefer to seek help from Q\u0026A website like","Rest":"Stack Overflow, despite the rich official documentation. Several researches have studied the limitations of the official application programming …"}}
{"Title":"Programming by Predicates","URL":"http://cseweb.ucsd.edu/~hpeleg/predicates-actainformatica19.pdf","Abstract":{"FirstLine":"Program synthesis is the problem of computing from a specification a program that","Rest":"implements it. New and popular variations on the synthesis problem accept specifications in formats that are easier for the human synthesis user to provide: input …"}}
{"Title":"Merging Weak and Active Supervision for Semantic Parsing","URL":"https://arxiv.org/pdf/1911.12986","Abstract":{"FirstLine":"A semantic parser maps natural language commands (NLs) from the users to executable","Rest":"meaning representations (MRs), which are later executed in certain environment to obtain user-desired results. The fully-supervised training of such …"}}
{"Title":"Combining Program Analysis and Statistical Language Model for Code Statement Completion","URL":"https://arxiv.org/pdf/1911.07781","Abstract":{"FirstLine":"Automatic code completion helps improve developers' productivity in their programming","Rest":"tasks. A program contains instructions expressed via code statements, which are considered as the basic units of program execution. In this paper, we …"}}
{"Title":"Exploring Robust Neural Methods in Inductive Program Synhthesis","URL":"http://www.ourpropeller.com/RobustMethodsIPS.pdf","Abstract":{"FirstLine":"ABSTRACT Inductive Program Synthesis (IPS) is an attractive goal for AI researchers as it","Rest":"provides a solution to the problem of getting programs to write code. Recent work has shown that neural networks are efficient tools for improving the …"}}
{"Title":"Neural Relational Inference with Fast Modular Meta-learning","URL":"https://papers.nips.cc/paper/9353-neural-relational-inference-with-fast-modular-meta-learning.pdf","Abstract":{"FirstLine":"Graph neural networks (GNNs) are effective models for many dynamical systems consisting","Rest":"of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types of interactions …"}}
{"Title":"Word Embedding Algorithms as Generalized Low Rank Models and their Canonical Form","URL":"https://arxiv.org/pdf/1911.02639","Abstract":{"FirstLine":"Word embedding algorithms produce very reliable feature representations of words that are","Rest":"used by neural network models across a constantly growing multitude of NLP tasks. As such, it is imperative for NLP practitioners to understand how their …"}}
{"Title":"Disentangling Interpretable Generative Parameters of Random and Real-World Graphs","URL":"https://arxiv.org/pdf/1910.05639","Abstract":{"FirstLine":"While a wide range of interpretable generative procedures for graphs exist, matching","Rest":"observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real …"}}
{"Title":"Online Robustness Training for Deep Reinforcement Learning","URL":"https://arxiv.org/pdf/1911.00887","Abstract":{"FirstLine":"In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted","Rest":"states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks …"}}
{"Title":"Automatic Unit Test Amplification For DevOps","URL":"https://tel.archives-ouvertes.fr/tel-02396530/document","Abstract":{"FirstLine":"Over the last decade, strong unit testing has become an essential component of any","Rest":"serious software project, whether in industry or academia. The agile development movement has contributed to this cultural change with the global dissemination of …"}}
{"Title":"Transferring Java Comments Based on Program Static Analysis","URL":"https://link.springer.com/chapter/10.1007/978-3-030-30952-7_64","Abstract":{"FirstLine":"In the process of software development and maintenance, code comments can help developers","Rest":"reduce the time of reading source code, and thus improve their work efficiency. For large Java software projects, comments tend to appear in front of the …"}}
{"Title":"LSC: Online Auto-Update Smart Contracts for Fortifying Blockchain-Based Log Systems","URL":"https://www.sciencedirect.com/science/article/pii/S0020025519309260","Abstract":{"FirstLine":"Smart contracts allow verifiable operations to be executed in blockchains, bringing new","Rest":"possibilities for trust establishment in trustless scenarios. However, smart contracts are cumbersome when used as security mechanisms in security scenarios …"}}
{"Title":"Deep Learning for Symbolic Mathematics","URL":"https://arxiv.org/pdf/1912.01412","Abstract":{"FirstLine":"Neural networks have a reputation for being better at solving statistical or approximate","Rest":"problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in …"}}
{"Title":"THE MOUNTAINS AS SACRED SPACES: CHURCH, PLACE, AND CULTURE IN NORTH CAROLINA APPALACHIAN MOUNTAIN POETRY ALANA D. DAGENHART","URL":"http://books.google.com/books?hl=en\u0026lr=lang_en\u0026id=ahHCDwAAQBAJ\u0026oi=fnd\u0026pg=PA45\u0026dq=%22Big+Code%22\u0026ots=SwNR2plkpl\u0026sig=K2L64NCMGMRRgJVxhNPGLwPnptc","Abstract":{"FirstLine":"… Alana D. Dagenhart 49 ly heard, but not understood by people, but “Indianssaid the","Rest":"peaks/were talking to each other in/the idiom that mountainsuse/across the mighty distances,/with giant syllables and rests,” as if some …"}}
{"Title":"Regularizing Variational Autoencoders for Molecular Graph Generation","URL":"https://link.springer.com/chapter/10.1007/978-3-030-36802-9_50","Abstract":{"FirstLine":"Deep generative models for graphs are promising for being able to sidestep expensive","Rest":"search procedures in the huge space of chemical compounds. However, incorporating complex and non-differentiable property metrics into a generative …"}}
{"Title":"Speech Recognition with Augmented Synthesized Speech","URL":"https://arxiv.org/pdf/1909.11699","Abstract":{"FirstLine":"Recent success of the Tacotron speech synthesis architecture and its variants in","Rest":"producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific …"}}
{"Title":"Type Safety with JSON Subschema","URL":"https://arxiv.org/pdf/1911.12651","Abstract":{"FirstLine":"JSON is a popular data format used pervasively in web APIs, cloud computing, NoSQL","Rest":"databases, and increasingly also machine learning. JSON Schema is a language for declaring the structure of valid JSON data. There are validators that can …"}}
{"Title":"Zoea--Composable Inductive Programming Without Limits","URL":"https://arxiv.org/pdf/1911.08286","Abstract":{"FirstLine":"Automatic generation of software from some form of specification has been a long standing","Rest":"goal of computer science research. To date successful results have been reported for the production of relatively small programs. This paper presents Zoea …"}}
{"Title":"A Survey of Compiler Testing","URL":"https://software-lab.org/publications/csur2019_compiler_testing.pdf","Abstract":{"FirstLine":"Compilers are important tools because they are a central piece of infrastructure for","Rest":"building other software. Virtually every program that runs on a computer, ranging from operating systems over web browsers to small scripts written by end-users, has …"}}
{"Title":"The Internet of Things and Machine Learning, Solutions for Urban Infrastructure Management","URL":"https://link.springer.com/chapter/10.1007/978-3-030-22044-0_13","Abstract":{"FirstLine":"Urban infrastructure management requires the ability to reason about a large-scale","Rest":"complex system: What is the state of the system? How can it be compactly represented and quantified? How is the system likely to evolve? Reasoning calls for …"}}
{"Title":"Beyond the Single Neuron Convex Barrier for Neural Network Certification","URL":"https://files.sri.inf.ethz.ch/website/papers/neurips19_krelu.pdf","Abstract":{"FirstLine":"We propose a new parametric framework, called k-ReLU, for computing precise and scalable","Rest":"convex relaxations used to certify neural networks. The key idea is to approximate the output of multiple ReLUs in a layer jointly instead of separately. This …"}}
{"Title":"Multi-Modal Attention Network Learning for Semantic Source Code Retrieval","URL":"https://arxiv.org/pdf/1909.13516","Abstract":{"FirstLine":"Code retrieval techniques and tools have been playing a key role in facilitating software","Rest":"developers to retrieve existing code fragments from available open-source repositories given a user query. Despite the existing efforts in improving the …"}}
{"Title":"Neural Speech Translation using Lattice Transformations and Graph Networks","URL":"https://www.aclweb.org/anthology/D19-5304.pdf","Abstract":{"FirstLine":"Speech translation systems usually follow a pipeline approach, using word lattices as an","Rest":"intermediate representation. However, previous work assume access to the original transcriptions used to train the ASR system, which can limit applicability in …"}}
{"Title":"Multimodal Machine Translation through Visuals and Speech","URL":"https://arxiv.org/pdf/1911.12798","Abstract":{"FirstLine":"Multimodal machine translation involves drawing information from more than one modality,","Rest":"based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken …"}}
{"Title":"DLTPy: Deep Learning Type Inference of Python Function Signatures using Natural Language Context","URL":"https://arxiv.org/pdf/1912.00680","Abstract":{"FirstLine":"Due to the rise of machine learning, Python is an increasingly popular programming","Rest":"language. Python, however, is dynamically typed. Dynamic typing has shown to have drawbacks when a project grows, while at the same time it improves developer …"}}
{"Title":"Program Synthesis for Programmers","URL":"http://www.cs.technion.ac.il/users/wwwb/cgi-bin/tr-get.cgi/2019/PHD/PHD-2019-11.pdf","Abstract":{"FirstLine":"Recent years have seen great progress in automated synthesis techniques that can","Rest":"automatically generate code based on some intent expressed by the user, but communicating this intent remains a major challenge. When the expressed intent is …"}}
{"Title":"Enabling Efficient Parallelism for Applications with Dependences and Irregular Memory Accesses","URL":"https://etd.ohiolink.edu/!etd.send_file?accession=osu1563461701172592\u0026disposition=inline","Abstract":{"FirstLine":"Page 1. Enabling Efficient Parallelism for Applications with Dependences and","Rest":"IrregularMemory Accesses Dissertation Presented in Partial Fulfillment of the Requirements forthe Degree Doctor of Philosophy in the Graduate School of The Ohio State University …"}}
{"Title":"Embedding Symbolic Knowledge into Deep Networks","URL":"http://papers.nips.cc/paper/8676-embedding-symbolic-knowledge-into-deep-networks.pdf","Abstract":{"FirstLine":"In this work, we aim to leverage prior symbolic knowledge to improve the performance of","Rest":"deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augmented Graph …"}}
{"Title":"Machine Learning On Complex Networks: Dynamical Fingerprints, Embeddings and Feature Engineering","URL":"https://dial.uclouvain.be/pr/boreal/object/boreal%3A222927/datastream/PDF_01/view","Abstract":{"FirstLine":"Complex networks emerge as a natural framework to describe real-life phenomena involving","Rest":"a group of entities and their interactions, ie, a social network. Furthermore, other problems involve a collection of networks, such as multi-layer, temporal, or …"}}
{"Title":"Coding as another language: a pedagogical approach for teaching computer science in early childhood","URL":"https://link.springer.com/article/10.1007/s40692-019-00147-3","Abstract":{"FirstLine":"Computer programming is an essential skill in the 21st century and new policies and","Rest":"frameworks aim at preparing students for computer science-related professions. Today, the development of new interfaces and block-programming languages …"}}
{"Title":"Novel positional encodings to enable tree-based transformers","URL":"http://papers.nips.cc/paper/9376-novel-positional-encodings-to-enable-tree-based-transformers.pdf","Abstract":{"FirstLine":"Neural models optimized for tree-based problems are of great value in tasks like SQL","Rest":"query extraction and program synthesis. On sequence-structured data, transformers have been shown to learn relationships across arbitrary pairs of positions more …"}}
{"Title":"Applications of Text Mining Techniques on Automated Software System Verification","URL":"https://prism.ucalgary.ca/bitstream/handle/1880/111013/ucalgary_2019_miryeganeh_nima.pdf?sequence=3\u0026isAllowed=y","Abstract":{"FirstLine":"Software Verification and Validation (V\u0026V) is an essential task in software engineering.","Rest":"Software systems are becoming larger and more complex and as a result, a manual V\u0026V process is getting more time-consuming and expensive. Text …"}}
{"Title":"Memory Augmented Recursive Neural Networks","URL":"https://arxiv.org/pdf/1911.01545","Abstract":{"FirstLine":"Recursive neural networks have shown an impressive performance for modeling compositional","Rest":"data compared to their recurrent counterparts. Although recursive neural networks are better at capturing long range dependencies, their …"}}
{"Title":"Concealment of iris features based on artificial noises","URL":"https://onlinelibrary.wiley.com/doi/pdf/10.4218/etrij.2019-0145","Abstract":{"FirstLine":"Although iris recognition verification is considered to be the safest method of biometric","Rest":"verification, studies have shown that iris features may be illegally used. To protect iris features and further improve the security of iris recognition and …"}}
{"Title":"Abstraction Mechanism on Neural Machine Translation Models for Automated Program Repair","URL":"https://uwspace.uwaterloo.ca/bitstream/handle/10012/15119/Wei_Moshi.pdf?sequence=1","Abstract":{"FirstLine":"Bug fixing is a time-consuming task in software development. Automated bug repair tools","Rest":"are created to fix programs with little or no human effort. There are many existing tools based on the generate-and-validate (G\u0026V) approach, which is an …"}}
{"Title":"A multi-stage anomaly detection scheme for augmenting the security in IoT-enabled applications","URL":"https://www.sciencedirect.com/science/article/pii/S0167739X19319703","Abstract":{"FirstLine":"The synergy between data security and high intensive computing has envisioned the way to","Rest":"robust anomaly detection schemes which in turn necessitates the need for efficient data analysis. Data clustering is one of the most important components of …"}}
{"Title":"Program Synthesis by Type-Guided Abstraction Refinement","URL":"https://arxiv.org/pdf/1911.04091","Abstract":{"FirstLine":"We consider the problem of type-directed component based synthesis where, given a set of","Rest":"(typed) components and a query type, the goal is to synthesize a term that inhabits the query. Classical approaches based on proof search in intuitionistic …"}}
{"Title":"A comparison of end-to-end models for long-form speech recognition","URL":"https://arxiv.org/pdf/1911.02242","Abstract":{"FirstLine":"End-to-end automatic speech recognition (ASR) models, including both attention-based","Rest":"models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies …"}}
{"Title":"GPU Algorithm for Earliest Arrival Time Problem in Public Transport Networks","URL":"https://arxiv.org/pdf/1912.00966","Abstract":{"FirstLine":"Given a temporal graph G, a source vertex s, and a departure time at source vertex t_s,","Rest":"the earliest arrival time problem EAT is to start from s on or after t_s and reach all the vertices in G as early as possible. Ni et al. have proposed a parallel algorithm for …"}}
{"Title":"OSAIFU: A Source Code Factorizer on Android Studio","URL":"https://ieeexplore.ieee.org/abstract/document/8918942/","Abstract":{"FirstLine":"Programs written in the event-driven style that are typical of mobile and/or Web","Rest":"applications are not easy to read through. For the purpose of reducing the burden put on software developers, we propose a tool for supporting program understanding …"}}
{"Title":"Neural Attribution for Semantic Bug-Localization in Student Programs","URL":"http://www.iisc-seal.net/publications/neurips2019.pdf","Abstract":{"FirstLine":"Providing feedback is an integral part of teaching. Most open online courses on","Rest":"programming make use of automated grading systems to support programming assignments and give real-time feedback. These systems usually rely on test results …"}}
{"Title":"Marking Mechanism in Sequence-to-sequence Model for Mapping Language to Logical Form","URL":"https://ieeexplore.ieee.org/abstract/document/8919471/","Abstract":{"FirstLine":"Semantic parsing in Natural language processing (NLP) is a challenging task, which has","Rest":"been studied for many years. The main purpose is to model the language as a logical form like a machine translation task. Recently, an approach which uses a …"}}
{"Title":"Augmented Example-based Synthesis using Relational Perturbation Properties","URL":"https://www.cs.purdue.edu/homes/roopsha/papers/sketchax_popl20.pdf","Abstract":{"FirstLine":"Authors' addresses: Shengwei An, Purdue University, USA, an93@ purdue. edu; Rishabh","Rest":"Singh, Google Brain, USA, rising@ google. com; Sasa Misailovic, UIUC, USA, misailo@ illinois. edu; Roopsha Samanta, Purdue University, USA, roopsha …"}}
{"Title":"Compiler Auto-Vectorization with Imitation Learning","URL":"https://papers.nips.cc/paper/9604-compiler-auto-vectorization-with-imitation-learning.pdf","Abstract":{"FirstLine":"Modern microprocessors are equipped with single instruction multiple data (SIMD) or","Rest":"vector instruction sets which allow compilers to exploit fine-grained data level parallelism. To exploit this parallelism, compilers employ auto-vectorization …"}}
{"Title":"CPC: automatically classifying and propagating natural language comments via program analysis","URL":"https://rucore.libraries.rutgers.edu/rutgers-lib/61591/PDF/1/play/","Abstract":{"FirstLine":"Modern software systems usually contain enormous code comments which provide abundant","Rest":"information that have been lever-aged to help perform various software engineering tasks, such as bug detection, specification inference, and code …"}}
{"Title":"Deep Representation Learning for Code Smells Detection using Variational Auto-Encoder","URL":"https://ieeexplore.ieee.org/abstract/document/8851854/","Abstract":{"FirstLine":"Detecting code smells is an important research problem in the software maintenance. It","Rest":"assists the subsequent steps of the refactoring process so as to improve the quality of the software system. However, most of existing approaches …"}}
{"Title":"Formal Verification of Workflow Policies for Smart Contracts in Azure Blockchain","URL":"https://www.cs.utexas.edu/~ypwang/pubs/vstte19.pdf","Abstract":{"FirstLine":"Ensuring correctness of smart contracts is paramount to ensuring trust in","Rest":"blockchain-based systems. This paper studies the safety and security of smart contracts in the Azure Blockchain Workbench, an enterprise Blockchain-as-a-Service offering from …"}}
{"Title":"Learning from Examples to Find Fully Qualified Names of API Elements in Code Snippets","URL":"https://www.researchgate.net/profile/C_M_Khaled_Saifullah/publication/336881435_Learning_from_Examples_to_Find_Fully_Qualified_Names_of_API_Elements_in_Code_Snippets/links/5db895ba92851c81801492be/Learning-from-Examples-to-Find-Fully-Qualified-Names-of-API-Elements-in-Code-Snippets.pdf","Abstract":{"FirstLine":"Developers often reuse code snippets from online forums, such as Stack Overflow, to learn","Rest":"API usages of software frameworks or libraries. These code snippets often contain ambiguous undeclared external references. Such external references make …"}}
{"Title":"Selective Monitoring Without Delay for Probabilistic System","URL":"http://perso.eleves.ens-rennes.fr/people/julie.parreaux/Parreaux_rapportStageM1.pdf","Abstract":{"FirstLine":"Monitoring is an efficient tool to check correctness in runtime. A monitor observes the","Rest":"output produced by a Markov Chain and decides if the run is correct or faulty. A selective monitor chooses the observed letters with a policy. It skips letters to reduce …"}}
{"Title":"Recommending Exception Handling Code","URL":"https://ieeexplore.ieee.org/abstract/document/8919036/","Abstract":{"FirstLine":"Exception handling is an advanced programming technique to prevent run-time errors or","Rest":"crashes for modern software systems. However, inexperienced programmers might fail to write proper exception handling code in their programs. In …"}}
{"Title":"Systems and methods for generating and using dynamic and localized route-based environmental information","URL":"https://patentimages.storage.googleapis.com/80/33/fa/4ca64b248964d8/US10408635.pdf","Abstract":{"FirstLine":"Methods, systems, and computer-readable media for generating localized environmental","Rest":"information along a route of travel are generally described, for example, to notify users of travel conditions along a specific route and/or to generate …"}}
{"Title":"Graph Enhanced Cross-Domain Text-to-SQL Generation","URL":"https://www.aclweb.org/anthology/D19-5319.pdf","Abstract":{"FirstLine":"Semantic parsing is a fundamental problem in natural language understanding, as it","Rest":"involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches …"}}
{"Title":"Software Engineering Meets Deep Learning: A Literature Review","URL":"https://arxiv.org/pdf/1909.11436","Abstract":{"FirstLine":"Deep learning (DL) is being used nowadays in many traditional software engineering (SE)","Rest":"problems and tasks, such as software documentation, defect prediction, and software testing. However, since the renaissance of DL techniques is …"}}
{"Title":"Efficient Graph Generation with Graph Recurrent Attention Networks","URL":"https://arxiv.org/pdf/1910.00760","Abstract":{"FirstLine":"We propose a new family of efficient and expressive deep generative models of graphs,","Rest":"called Graph Recurrent Attention Networks (GRANs). Our model generates graphs one block of nodes and associated edges at a time. The block size and …"}}
{"Title":"Does your code need comment?","URL":"https://onlinelibrary.wiley.com/doi/abs/10.1002/spe.2772","Abstract":{"FirstLine":"Code comments convey information about the programmers' intention in a more explicit but","Rest":"less rigorous manner than source code. This information can assist programmers in various tasks, such as code comprehension, reuse, and …"}}
{"Title":"Mode Personalization in Trip-Based Transit Routing","URL":"http://drops.dagstuhl.de/opus/volltexte/2019/11425/pdf/OASIcs-ATMOS-2019-13.pdf","Abstract":{"FirstLine":"We study the problem of finding bi-criteria Pareto optimal journeys in public transit","Rest":"networks. We extend the Trip-Based Public Transit Routing (TB) approach [Sascha Witt, 2015] to allow for users to select modes of interest at query time. As a first step …"}}
{"Title":"Combining Constraint Languages via Abstract Interpretation","URL":"http://hyc.io/papers/ictai2019.pdf","Abstract":{"FirstLine":"Constraint programming initially aims to be a declarative paradigm, but its quest for","Rest":"efficiency is mainly achieved through the development of ad-hoc algorithms, which are encapsulated in global constraints. In this paper, we explore the idea of …"}}
{"Title":"Efficient Precise Dynamic Data Race Detection for CPU and GPU","URL":"http://search.proquest.com/openview/30286d466b8904f517e5d16465a1c7df/1?pq-origsite=gscholar\u0026cbl=18750\u0026diss=y","Abstract":{"FirstLine":"Data races are notorious bugs. They introduce non-determinism in programs behavior,","Rest":"complicate programs semantics, making it challenging to debug parallel programs. To make parallel programming easier, efficient data race detection has …"}}
{"Title":"Efficient Scalable Thread-Safety-Violation Detection","URL":"http://people.cs.uchicago.edu/~cstjygpl/sosp19-tsvd.pdf","Abstract":{"FirstLine":"Concurrency bugs are hard to find, reproduce, and debug. They often escape rigorous","Rest":"in-house testing, but result in large-scale outages in production. Existing concurrencybug detection techniques unfortunately cannot be part of industry's …"}}
{"Title":"NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning","URL":"https://arxiv.org/pdf/1909.13639","Abstract":{"FirstLine":"One of the key challenges arising when compilers vectorize loops for today's","Rest":"SIMD-compatible architectures is whether to vectorize and/or interleave. Then, the compiler has to determine how many instructions to pack together and how many loop …"}}
{"Title":"Why is Developing Machine Learning Applications Challenging? A Study on Stack Overflow Posts","URL":"https://ieeexplore.ieee.org/abstract/document/8870187/","Abstract":{"FirstLine":"As smart and automated applications pervade our lives, an increasing number of software","Rest":"developers are required to incorporate machine learning (ML) techniques into application development. However, acquiring the ML skill set can be nontrivial …"}}
{"Title":"Towards Robust Direct Perception Networks for Automated Driving","URL":"https://arxiv.org/pdf/1909.13600","Abstract":{"FirstLine":"We consider the problem of engineering robust direct perception neural networks with","Rest":"output being regression. Such networks take high dimensional input image data, and they produce affordances such as the curvature of the upcoming road segment …"}}
{"Title":"Property Invariant Embedding for Automated Reasoning","URL":"https://arxiv.org/pdf/1911.12073","Abstract":{"FirstLine":"Automated reasoning and theorem proving have recently become major challenges for machine","Rest":"learning. In other domains, representations that are able to abstract over unimportant transformations, such as abstraction over translations and rotations in …"}}
{"Title":"Towards neural networks that provably know when they don't know","URL":"https://arxiv.org/pdf/1909.12180","Abstract":{"FirstLine":"It has recently been shown that ReLU networks produce arbitrarily over-confident","Rest":"predictions far away from the training data. Thus, ReLU networks do not know when they don't know. However, this is a highly important property in safety critical …"}}
{"Title":"Sequence Model Design for Code Completion in the Modern IDE","URL":"https://aye.science/aye-icse-2020.pdf","Abstract":{"FirstLine":"Code completion is a tremendously popular tool for coding assistance, implemented across","Rest":"a wide range of programming languages and environments. In An Empirical Investigation of Code Completion Usage by Professional Software Developers …"}}
{"Title":"Coda: An End-to-End Neural Program Decompiler","URL":"http://papers.nips.cc/paper/8628-coda-an-end-to-end-neural-program-decompiler.pdf","Abstract":{"FirstLine":"Reverse engineering of binary executables is a critical problem in the computer security","Rest":"domain. On the one hand, malicious parties may recover interpretable source codes from the software products to gain commercial advantages. On the …"}}
{"Title":"Parallel Iterative Edit Models for Local Sequence Transduction","URL":"https://arxiv.org/pdf/1910.02893","Abstract":{"FirstLine":"We present a Parallel Iterative Edit (PIE) model for the problem of local sequence","Rest":"transduction arising in tasks like Grammatical error correction (GEC). Recent approaches are based on the popular encoder-decoder (ED) model for sequence to …"}}
{"Title":"Graph normalizing flows","URL":"http://papers.nips.cc/paper/9510-graph-normalizing-flows.pdf","Abstract":{"FirstLine":"We introduce graph normalizing flows: a new, reversible graph neural network model for","Rest":"prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory …"}}
{"Title":"Empirical Study of Fault Introduction Focusing on the Similarity among Local Variable Names","URL":"http://ceur-ws.org/Vol-2511/QuASoQ-01.pdf","Abstract":{"FirstLine":"Well-chosen variable names play significant roles in program comprehension and","Rest":"high-quality software development and maintenance. However, even though all variables have easyto-understand names, attention needs to be paid to the similarity …"}}
{"Title":"NutBaaS: A Blockchain-as-a-Service Platform","URL":"https://ieeexplore.ieee.org/iel7/6287639/6514899/08840920.pdf","Abstract":{"FirstLine":"Blockchain, originated from Bitcoin system, has drawn intense attention from the academic","Rest":"community because of its decentralization, persistency, anonymity and auditability. In the past decade, the blockchain technology has evolved and became …"}}
{"Title":"A (CO) ALGEBRAIC APPROACH TO PROGRAMMING AND VERIFYING COMPUTER NETWORKS","URL":"https://smolka.st/papers/phd-thesis.pdf","Abstract":{"FirstLine":"As computer networks have grown into some of the most complex and critical computing","Rest":"systems today, the means of configuring them have not kept up: they remain manual, low-level, and ad-hoc. This makes network operations expensive …"}}
{"Title":"Progressive Processing of System-Behavioral Query","URL":"https://engineering.case.edu/groups/xusheng-xiao/sites/engineering.case.edu.groups.xusheng-xiao/files/docs/acsac19-final143.pdf","Abstract":{"FirstLine":"System monitoring has recently emerged as an effective way to analyze and counter","Rest":"advanced cyber attacks. The monitoring data records a series of system events and provides a global view of system behaviors in an organization. Querying such data to …"}}
{"Title":"Inverse‐QSPR for de novo design: a review","URL":"https://onlinelibrary.wiley.com/doi/abs/10.1002/minf.201900087","Abstract":{"FirstLine":"The use of computer tools to solve chemistry‐related problems–chemoinformatics–has given","Rest":"rise to a large number of publications. Among all chemoinformatics techniques, the use of statistically based approaches for property predictions has …"}}
{"Title":"Semantic Preserving Generative Adversarial Models","URL":"https://arxiv.org/pdf/1910.02804","Abstract":{"FirstLine":"We introduce generative adversarial models in which the discriminator is replaced by a","Rest":"calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove that the actual and generated data differ …"}}
{"Title":"CLN2INV: Learning Loop Invariants with Continuous Logic Networks","URL":"https://arxiv.org/pdf/1909.11542","Abstract":{"FirstLine":"Program verification offers a framework for ensuring program correctness and therefore","Rest":"systematically eliminating different classes of bugs. Inferring loop invariants is one of the main challenges behind automated verification of real-world programs …"}}
{"Title":"Static Detection of Event-Driven Races in HTML5-Based Mobile Apps","URL":"https://link.springer.com/chapter/10.1007/978-3-030-35092-5_3","Abstract":{"FirstLine":"HTML5-based mobile apps are developed using standard web technologies such as HTML5, CSS,","Rest":"JavaScript, so they may also face with event-based races as web apps. The races in such mobile apps can be caused by various sources of …"}}
{"Title":"A Survey on Research of Code Comment Auto Generation","URL":"https://iopscience.iop.org/article/10.1088/1742-6596/1345/3/032010/pdf","Abstract":{"FirstLine":"A code comment is an explanation of the code. As an important part of software","Rest":"development process, code comment plays an important role in software maintenance, software reuse and other fields. Automatic generation of code …"}}
{"Title":"An Evalutation of Programming Language Models' performance on Software Defect Detection","URL":"https://arxiv.org/pdf/1909.10309","Abstract":{"FirstLine":"This dissertation presents an evaluation of several language models on software defect","Rest":"datasets. A language Model (LM)\" can provide word representation and probability indication of word sequences as the core component of an NLP system.\" …"}}
{"Title":"A Generative Model for Molecular Distance Geometry","URL":"https://arxiv.org/pdf/1909.11459","Abstract":{"FirstLine":"Computing equilibrium states for many-body systems, such as molecules, is a long-standing","Rest":"challenge. In the absence of methods for generating statistically independent samples, great computational effort is invested in simulating these …"}}
{"Title":"Méthodes d'apprentissage statistique pour le criblage virtuel de médicament Machine learning approaches for drug virtual screening","URL":"https://pdfs.semanticscholar.org/0aa6/8f2d263e230434606bb24eb132f636023012.pdf","Abstract":{"FirstLine":"Cystic Fibrosis (CF) is the most common genetic disease among Caucasians, affecting","Rest":"approximately one in 3500 birth [193], and one person in 25 is an asymptomatic heterozygote carrier. It is an autosomal recessive genetic disease …"}}
{"Title":"Four presumed gaps in the software engineering research community's knowledge","URL":"https://arxiv.org/pdf/1911.09971","Abstract":{"FirstLine":"Background: The state of the art in software engineering consists of a myriad of","Rest":"contributions and the gaps between them; it is difficult to characterize. Questions: In order to help understanding the state of the art, can we identify gaps in our …"}}
{"Title":"SoCodeCNN: Program Source Code for Visual CNN Classification Using Computer Vision Methodology","URL":"https://ieeexplore.ieee.org/iel7/6287639/8600701/08882216.pdf","Abstract":{"FirstLine":"Automated feature extraction from program source-code such that proper computing","Rest":"resources could be allocated to the program is very difficult given the current state of technology. Therefore, conventional methods call for skilled human intervention in …"}}
{"Title":"TreeGen: A Tree-Based Transformer Architecture for Code Generation","URL":"https://arxiv.org/pdf/1911.09983","Abstract":{"FirstLine":"A code generation system generates programming language code based on an input natural","Rest":"language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two …"}}
{"Title":"Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models","URL":"https://arxiv.org/pdf/1911.09762","Abstract":{"FirstLine":"In this paper, we propose to use pre-trained features from end-to-end ASR models to solve","Rest":"the speech sentiment analysis problem as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from …"}}
{"Title":"ASTToken2Vec: An Embedding Method for Neural Code Completion","URL":"http://jssst.or.jp/files/user/taikai/2019/GENERAL/general2-2.pdf","Abstract":{"FirstLine":"Code completion systems help programmers to write code more efficiently and to reduce","Rest":"typographical errors by automatically suggesting the code fragment that the programmers likely to write next. This work attempts to increase prediction …"}}