TY - CONF AU - Richter, Cedric AU - Haltermann, Jan Frederik AU - Jakobs, Marie-Christine AU - Pauck, Felix AU - Schott, Stefan AU - Wehrheim, Heike ID - 35426 T2 - 37th IEEE/ACM International Conference on Automated Software Engineering TI - Are Neural Bug Detectors Comparable to Software Developers on Variable Misuse Bugs? ER - TY - CONF AU - Pauck, Felix ID - 35427 T2 - 37th IEEE/ACM International Conference on Automated Software Engineering TI - Scaling Arbitrary Android App Analyses ER - TY - CONF AU - Ahmed, Qazi Arbab AU - Awais, Muhammad AU - Platzner, Marco ID - 44194 T2 - The 24th International Symposium on Quality Electronic Design (ISQED'23), San Francisco, Califorina USA TI - MAAS: Hiding Trojans in Approximate Circuits ER - TY - THES AU - Pauck, Felix ID - 43108 TI - Cooperative Android App Analysis ER - TY - THES AB - Reading between the lines has so far been reserved for humans. The present dissertation addresses this research gap using machine learning methods. Implicit expressions are not comprehensible by computers and cannot be localized in the text. However, many texts arise on interpersonal topics that, unlike commercial evaluation texts, often imply information only by means of longer phrases. Examples are the kindness and the attentiveness of a doctor, which are only paraphrased (“he didn’t even look me in the eye”). The analysis of such data, especially the identification and localization of implicit statements, is a research gap (1). This work uses so-called Aspect-based Sentiment Analysis as a method for this purpose. It remains open how the aspect categories to be extracted can be discovered and thematically delineated based on the data (2). Furthermore, it is not yet explored how a collection of tools should look like, with which implicit phrases can be identified and thus made explicit (3). Last, it is an open question how to correlate the identified phrases from the text data with other data, including the investigation of the relationship between quantitative scores (e.g., school grades) and the thematically related text (4). Based on these research gaps, the research question is posed as follows: Using text mining methods, how can implicit rating content be properly interpreted and thus made explicit before it is automatically categorized and quantified? The uniqueness of this dissertation is based on the automated recognition of implicit linguistic statements alongside explicit statements. These are identified in unstructured text data so that features expressed only in the text can later be compared across data sources, even though they were not included in rating categories such as stars or school grades. German-language physician ratings from websites in three countries serve as the sample domain. The solution approach consists of data creation, a pipeline for text processing and analyses based on this. In the data creation, aspect classes are identified and delineated across platforms and marked in text data. This results in six datasets with over 70,000 annotated sentences and detailed guidelines. The models that were created based on the training data extract and categorize the aspects. In addition, the sentiment polarity and the evaluation weight, i. e., the importance of each phrase, are determined. The models, which are combined in a pipeline, are used in a prototype in the form of a web application. The analyses built on the pipeline quantify the rating contents by linking the obtained information with further data, thus allowing new insights. As a result, a toolbox is provided to identify quantifiable rating content and categories using text mining for a sample domain. This is used to evaluate the approach, which in principle can also be adapted to any other domain. AU - Kersting, Joschka ID - 44323 TI - Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining ER - TY - CHAP AU - Wehrheim, Heike AU - Platzner, Marco AU - Bodden, Eric AU - Schubert, Philipp AU - Pauck, Felix AU - Jakobs, Marie-Christine ED - Haake, Claus-Jochen ED - Meyer auf der Heide, Friedhelm ED - Platzner, Marco ED - Wachsmuth, Henning ED - Wehrheim, Heike ID - 45888 T2 - On-The-Fly Computing -- Individualized IT-services in dynamic markets TI - Verifying Software and Reconfigurable Hardware Services VL - 412 ER - TY - CHAP AU - Bäumer, Frederik Simon AU - Chen, Wei-Fan AU - Geierhos, Michaela AU - Kersting, Joschka AU - Wachsmuth, Henning ED - Haake, Claus-Jochen ED - Meyer auf der Heide, Friedhelm ED - Platzner, Marco ED - Wachsmuth, Henning ED - Wehrheim, Heike ID - 45882 T2 - On-The-Fly Computing -- Individualized IT-services in dynamic markets TI - Dialogue-based Requirement Compensation and Style-adjusted Data-to-text Generation VL - 412 ER - TY - CHAP AU - Hanselle, Jonas Manuel AU - Hüllermeier, Eyke AU - Mohr, Felix AU - Ngonga Ngomo, Axel-Cyrille AU - Sherif, Mohamed AU - Tornede, Alexander AU - Wever, Marcel Dominik ED - Haake, Claus-Jochen ED - Meyer auf der Heide, Friedhelm ED - Platzner, Marco ED - Wachsmuth, Henning ED - Wehrheim, Heike ID - 45884 T2 - On-The-Fly Computing -- Individualized IT-services in dynamic markets TI - Configuration and Evaluation VL - 412 ER - TY - CHAP AU - Wehrheim, Heike AU - Hüllermeier, Eyke AU - Becker, Steffen AU - Becker, Matthias AU - Richter, Cedric AU - Sharma, Arnab ED - Haake, Claus-Jochen ED - Meyer auf der Heide, Friedhelm ED - Platzner, Marco ED - Wachsmuth, Henning ED - Wehrheim, Heike ID - 45886 T2 - On-The-Fly Computing -- Individualized IT-services in dynamic markets TI - Composition Analysis in Unknown Contexts VL - 412 ER - TY - CHAP AB - We present a concept for quantifying evaluative phrases to later compare rating texts numerically instead of just relying on stars or grades. We achievethis by combining deep learning models in an aspect-based sentiment analysis pipeline along with sentiment weighting, polarity, and correlation analyses that combine deep learning results with metadata. The results provide new insights for the medical field. Our application domain, physician reviews, shows that there are millions of review texts on the Internet that cannot yet be comprehensively analyzed because previous studies have focused on explicit aspects from other domains (e.g., products). We identify, extract, and classify implicit and explicit aspect phrases equally from German-language review texts. To do so, we annotated aspect phrases representing reviews on numerous aspects of a physician, medical practice, or practice staff. We apply the best performing transformer model, XLM-RoBERTa, to a large physician review dataset and correlate the results with existing metadata. As a result, we can show different correlations between the sentiment polarity of certain aspect classes (e.g., friendliness, practice equipment) and physicians’ professions (e.g., surgeon, ophthalmologist). As a result, we have individual numerical scores that contain a variety of information based on deep learning algorithms that extract textual (evaluative) information and metadata from the Web. AU - Kersting, Joschka AU - Geierhos, Michaela ED - Cuzzocrea, Alfredo ED - Gusikhin, Oleg ED - Hammoudi, Slimane ED - Quix, Christoph ID - 46205 SN - 1865-0929 T2 - Data Management Technologies and Applications TI - Towards Comparable Ratings: Quantifying Evaluative Phrases in Physician Reviews VL - 1860 ER - TY - THES AU - Tornede, Alexander ID - 45780 TI - Advanced Algorithm Selection with Machine Learning: Handling Large Algorithm Sets, Learning From Censored Data, and Simplyfing Meta Level Decisions ER - TY - BOOK AB - In the proposal for our CRC in 2011, we formulated a vision of markets for IT services that describes an approach to the provision of such services that was novel at that time and, to a large extent, remains so today: „Our vision of on-the-fly computing is that of IT services individually and automatically configured and brought to execution from flexibly combinable services traded on markets. At the same time, we aim at organizing markets whose participants maintain a lively market of services through appropriate entrepreneurial actions.“ Over the last 12 years, we have developed methods and techniques to address problems critical to the convenient, efficient, and secure use of on-the-fly computing. Among other things, we have made the description of services more convenient by allowing natural language input, increased the quality of configured services through (natural language) interaction and more efficient configuration processes and analysis procedures, made the quality of (the products of) providers in the marketplace transparent through reputation systems, and increased the resource efficiency of execution through reconfigurable heterogeneous computing nodes and an integrated treatment of service description and configuration. We have also developed network infrastructures that have a high degree of adaptivity, scalability, efficiency, and reliability, and provide cryptographic guarantees of anonymity and security for market participants and their products and services. To demonstrate the pervasiveness of the OTF computing approach, we have implemented a proof-of-concept for OTF computing that can run typical scenarios of an OTF market. We illustrated the approach using a cutting-edge application scenario – automated machine learning (AutoML). Finally, we have been pushing our work for the perpetuation of On-The-Fly Computing beyond the SFB and sharing the expertise gained in the SFB in events with industry partners as well as transfer projects. This work required a broad spectrum of expertise. Computer scientists and economists with research interests such as computer networks and distributed algorithms, security and cryptography, software engineering and verification, configuration and machine learning, computer engineering and HPC, microeconomics and game theory, business informatics and management have successfully collaborated here. AU - Haake, Claus-Jochen AU - Meyer auf der Heide, Friedhelm AU - Platzner, Marco AU - Wachsmuth, Henning AU - Wehrheim, Heike ID - 45863 TI - On-The-Fly Computing -- Individualized IT-services in dynamic markets VL - 412 ER - TY - THES AU - König, Jürgen ID - 47833 TI - On the Membership and Correctness Problem for State Serializability and Value Opacity ER - TY - CONF AU - Witschen, Linus Matthias AU - Wiersema, Tobias AU - Reuter, Lucas David AU - Platzner, Marco ID - 29945 T2 - 2022 59th ACM/IEEE Design Automation Conference (DAC) TI - Search Space Characterization for Approximate Logic Synthesis ER - TY - CONF AU - Witschen, Linus Matthias AU - Wiersema, Tobias AU - Artmann, Matthias AU - Platzner, Marco ID - 29865 T2 - Design, Automation and Test in Europe (DATE) TI - MUSCAT: MUS-based Circuit Approximation Technique ER - TY - GEN AB - Algorithm configuration (AC) is concerned with the automated search of the most suitable parameter configuration of a parametrized algorithm. There is currently a wide variety of AC problem variants and methods proposed in the literature. Existing reviews do not take into account all derivatives of the AC problem, nor do they offer a complete classification scheme. To this end, we introduce taxonomies to describe the AC problem and features of configuration methods, respectively. We review existing AC literature within the lens of our taxonomies, outline relevant design choices of configuration approaches, contrast methods and problem variants against each other, and describe the state of AC in industry. Finally, our review provides researchers and practitioners with a look at future research directions in the field of AC. AU - Schede, Elias AU - Brandt, Jasmin AU - Tornede, Alexander AU - Wever, Marcel Dominik AU - Bengs, Viktor AU - Hüllermeier, Eyke AU - Tierney, Kevin ID - 30868 T2 - arXiv:2202.01651 TI - A Survey of Methods for Automated Algorithm Configuration ER - TY - CONF AB - Testing is one of the most frequent means of quality assurance for software. Property-based testing aims at generating test suites for checking code against user-defined properties. Test input generation is, however, most often independent of the property to be checked, and is instead based on random or user-defined data generation.In this paper, we present property-driven unit testing of functions with numerical inputs and outputs. Alike property-based testing, it allows users to define the properties to be tested for. Contrary to property-based testing, it also uses the property for a targeted generation of test inputs. Our approach is a form of learning-based testing where we first of all learn a model of a given black-box function using standard machine learning algorithms, and in a second step use model and property for test input generation. This allows us to test both predefined functions as well as machine learned regression models. Our experimental evaluation shows that our property-driven approach is more effective than standard property-based testing techniques. AU - Sharma, Arnab AU - Melnikov, Vitaly AU - Hüllermeier, Eyke AU - Wehrheim, Heike ID - 32311 T2 - Proceedings of the 10th IEEE/ACM International Conference on Formal Methods in Software Engineering (FormaliSE) TI - Property-Driven Testing of Black-Box Functions ER - TY - CONF AB - It is well known that different algorithms perform differently well on an instance of an algorithmic problem, motivating algorithm selection (AS): Given an instance of an algorithmic problem, which is the most suitable algorithm to solve it? As such, the AS problem has received considerable attention resulting in various approaches - many of which either solve a regression or ranking problem under the hood. Although both of these formulations yield very natural ways to tackle AS, they have considerable weaknesses. On the one hand, correctly predicting the performance of an algorithm on an instance is a sufficient, but not a necessary condition to produce a correct ranking over algorithms and in particular ranking the best algorithm first. On the other hand, classical ranking approaches often do not account for concrete performance values available in the training data, but only leverage rankings composed from such data. We propose HARRIS- Hybrid rAnking and RegRessIon foreSts - a new algorithm selector leveraging special forests, combining the strengths of both approaches while alleviating their weaknesses. HARRIS' decisions are based on a forest model, whose trees are created based on splits optimized on a hybrid ranking and regression loss function. As our preliminary experimental study on ASLib shows, HARRIS improves over standard algorithm selection approaches on some scenarios showing that combining ranking and regression in trees is indeed promising for AS. AU - Fehring, Lukass AU - Hanselle, Jonas Manuel AU - Tornede, Alexander ID - 34103 T2 - Workshop on Meta-Learning (MetaLearn 2022) @ NeurIPS 2022 TI - HARRIS: Hybrid Ranking and Regression Forests for Algorithm Selection ER - TY - JOUR AB - AbstractMany critical codebases are written in C, and most of them use preprocessor directives to encode variability, effectively encoding software product lines. These preprocessor directives, however, challenge any static code analysis. SPLlift, a previously presented approach for analyzing software product lines, is limited to Java programs that use a rather simple feature encoding and to analysis problems with a finite and ideally small domain. Other approaches that allow the analysis of real-world C software product lines use special-purpose analyses, preventing the reuse of existing analysis infrastructures and ignoring the progress made by the static analysis community. This work presents VarAlyzer, a novel static analysis approach for software product lines. VarAlyzer first transforms preprocessor constructs to plain C while preserving their variability and semantics. It then solves any given distributive analysis problem on transformed product lines in a variability-aware manner. VarAlyzer ’s analysis results are annotated with feature constraints that encode in which configurations each result holds. Our experiments with 95 compilation units of OpenSSL show that applying VarAlyzer enables one to conduct inter-procedural, flow-, field- and context-sensitive data-flow analyses on entire product lines for the first time, outperforming the product-based approach for highly-configurable systems. AU - Schubert, Philipp AU - Gazzillo, Paul AU - Patterson, Zach AU - Braha, Julian AU - Schiebel, Fabian AU - Hermann, Ben AU - Wei, Shiyi AU - Bodden, Eric ID - 30511 IS - 1 JF - Automated Software Engineering KW - inter-procedural static analysis KW - software product lines KW - preprocessor KW - LLVM KW - C/C++ SN - 0928-8910 TI - Static data-flow analysis for software product lines in C VL - 29 ER - TY - CONF AU - Richter, Cedric AU - Wehrheim, Heike ID - 32590 T2 - 2022 IEEE Conference on Software Testing, Verification and Validation (ICST) TI - Learning Realistic Mutations: Bug Creation for Neural Bug Detectors ER - TY - CONF AU - Richter, Cedric AU - Wehrheim, Heike ID - 32591 T2 - 2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR) TI - TSSB-3M: Mining single statement bugs at massive scale ER - TY - CONF AB - The creation of an RDF knowledge graph for a particular application commonly involves a pipeline of tools that transform a set ofinput data sources into an RDF knowledge graph in a process called dataset augmentation. The components of such augmentation pipelines often require extensive configuration to lead to satisfactory results. Thus, non-experts are often unable to use them. Wepresent an efficient supervised algorithm based on genetic programming for learning knowledge graph augmentation pipelines of arbitrary length. Our approach uses multi-expression learning to learn augmentation pipelines able to achieve a high F-measure on the training data. Our evaluation suggests that our approach can efficiently learn a larger class of RDF dataset augmentation tasks than the state of the art while using only a single training example. Even on the most complex augmentation problem we posed, our approach consistently achieves an average F1-measure of 99% in under 500 iterations with an average runtime of 16 seconds AU - Dreßler, Kevin AU - Sherif, Mohamed AU - Ngonga Ngomo, Axel-Cyrille ID - 31806 KW - 2022 RAKI SFB901 deer dice kevin knowgraphs limes ngonga sherif simba T2 - Proceedings of the 33rd ACM Conference on Hypertext and Hypermedia TI - ADAGIO - Automated Data Augmentation of Knowledge Graphs Using Multi-expression Learning ER - TY - CONF AU - Chen, Wei-Fan AU - Chen, Mei-Hua AU - Mudgal, Garima AU - Wachsmuth, Henning ID - 33274 T2 - Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022) TI - Analyzing Culture-Specific Argument Structures in Learner Essays ER - TY - CHAP AB - This work addresses the automatic resolution of software requirements. In the vision of On-The-Fly Computing, software services should be composed on demand, based solely on natural language input from human users. To enable this, we build a chatbot solution that works with human-in-the-loop support to receive, analyze, correct, and complete their software requirements. The chatbot is equipped with a natural language processing pipeline and a large knowledge base, as well as sophisticated dialogue management skills to enhance the user experience. Previous solutions have focused on analyzing software requirements to point out errors such as vagueness, ambiguity, or incompleteness. Our work shows how apps can collaborate with users to efficiently produce correct requirements. We developed and compared three different chatbot apps that can work with built-in knowledge. We rely on ChatterBot, DialoGPT and Rasa for this purpose. While DialoGPT provides its own knowledge base, Rasa is the best system to combine the text mining and knowledge solutions at our disposal. The evaluation shows that users accept 73% of the suggested answers from Rasa, while they accept only 63% from DialoGPT or even 36% from ChatterBot. AU - Kersting, Joschka AU - Ahmed, Mobeen AU - Geierhos, Michaela ED - Stephanidis, Constantine ED - Antona, Margherita ED - Ntoa, Stavroula ID - 32179 KW - On-The-Fly Computing KW - Chatbot KW - Knowledge Base SN - 1865-0929 T2 - HCI International 2022 Posters TI - Chatbot-Enhanced Requirements Resolution for Automated Service Compositions VL - 1580 ER - TY - CONF AB - This paper aims at discussing past limitations set in sentiment analysis research regarding explicit and implicit mentions of opinions. Previous studies have regularly neglected this question in favor of methodical research on standard-datasets. Furthermore, they were limited to linguistically less-diverse domains, such as commercial product reviews. We face this issue by annotating a German-language physician review dataset that contains numerous implicit, long, and complex statements that indicate aspect ratings, such as the physician’s friendliness. We discuss the nature of implicit statements and present various samples to illustrate the challenge described. AU - Kersting, Joschka AU - Bäumer, Frederik Simon ED - Kersting, Joschka ID - 31054 KW - Sentiment analysis KW - Natural language processing KW - Aspect phrase extraction T2 - Proceedings of the Fourteenth International Conference on Pervasive Patterns and Applications (PATTERNS 2022): Special Track AI-DRSWA: Maturing Artificial Intelligence - Data Science for Real-World Applications TI - Implicit Statements in Healthcare Reviews: A Challenge for Sentiment Analysis ER - TY - GEN AU - Chen, Mei-Hua AU - Mudgal, Garima AU - Chen, Wei-Fan AU - Wachsmuth, Henning ID - 31068 T2 - EUROCALL TI - Investigating the argumentation structures of EFL learners from diverse language backgrounds ER - TY - GEN AU - Fehring, Lukas ID - 33033 TI - Combined Ranking and Regression Trees for Algorithm Selection ER - TY - GEN AB - In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms. For decision problems such as satisfiability (SAT), quality typically refers to the algorithm's runtime. As the latter is known to exhibit a heavy-tail distribution, an algorithm is normally stopped when exceeding a predefined upper time limit. As a consequence, machine learning methods used to optimize an algorithm selection strategy in a data-driven manner need to deal with right-censored samples, a problem that has received little attention in the literature so far. In this work, we revisit multi-armed bandit algorithms for OAS and discuss their capability of dealing with the problem. Moreover, we adapt them towards runtime-oriented losses, allowing for partially censored data while keeping a space- and time-complexity independent of the time horizon. In an extensive experimental evaluation on an adapted version of the ASlib benchmark, we demonstrate that theoretically well-founded methods based on Thompson sampling perform specifically strong and improve in comparison to existing methods. AU - Tornede, Alexander AU - Bengs, Viktor AU - Hüllermeier, Eyke ID - 30867 T2 - Proceedings of the 36th AAAI Conference on Artificial Intelligence TI - Machine Learning for Online Algorithm Selection under Censored Feedback ER - TY - GEN AB - The problem of selecting an algorithm that appears most suitable for a specific instance of an algorithmic problem class, such as the Boolean satisfiability problem, is called instance-specific algorithm selection. Over the past decade, the problem has received considerable attention, resulting in a number of different methods for algorithm selection. Although most of these methods are based on machine learning, surprisingly little work has been done on meta learning, that is, on taking advantage of the complementarity of existing algorithm selection methods in order to combine them into a single superior algorithm selector. In this paper, we introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework, essentially combining ideas of meta learning and ensemble learning. In an extensive experimental evaluation, we demonstrate that ensembles of algorithm selectors can significantly outperform single algorithm selectors and have the potential to form the new state of the art in algorithm selection. AU - Tornede, Alexander AU - Gehring, Lukas AU - Tornede, Tanja AU - Wever, Marcel Dominik AU - Hüllermeier, Eyke ID - 30865 T2 - Machine Learning TI - Algorithm Selection on a Meta Level ER - TY - JOUR AB - AbstractHeated tool butt welding is a method often used for joining thermoplastics, especially when the components are made out of different materials. The quality of the connection between the components crucially depends on a suitable choice of the parameters of the welding process, such as heating time, temperature, and the precise way how the parts are then welded. Moreover, when different materials are to be joined, the parameter values need to be tailored to the specifics of the respective material. To this end, in this paper, three approaches to tailor the parameter values to optimize the quality of the connection are compared: a heuristic by Potente, statistical experimental design, and Bayesian optimization. With the suitability for practice in mind, a series of experiments are carried out with these approaches, and their capabilities of proposing well-performing parameter values are investigated. As a result, Bayesian optimization is found to yield peak performance, but the costs for optimization are substantial. In contrast, the Potente heuristic does not require any experimentation and recommends parameter values with competitive quality. AU - Gevers, Karina AU - Tornede, Alexander AU - Wever, Marcel Dominik AU - Schöppner, Volker AU - Hüllermeier, Eyke ID - 33090 JF - Welding in the World KW - Metals and Alloys KW - Mechanical Engineering KW - Mechanics of Materials SN - 0043-2288 TI - A comparison of heuristic, statistical, and machine learning methods for heated tool butt welding of two different materials ER - TY - THES AU - Witschen, Linus Matthias ID - 34041 TI - Frameworks and Methodologies for Search-based Approximate Logic Synthesis ER - TY - CONF AU - Ahmed, Qazi Arbab AU - Platzner, Marco ID - 32342 TI - On the Detection and Circumvention of Bitstream-Level Trojans in FPGAs ER - TY - GEN AB - This thesis aims to provide a bidirectional chatbot solution for the requirement engineering process. The Sonderforschungsbereich (SFB) 901 intends to provide the composition of software service On-the-Fly (OTF). The sub-project (B1) of the SFB 901 project deals with the parameters of service configuration. OTF Computing aims to eradicate the dependency on the requirement engineers for the software development process. However, there is no existing bidirectional chatbot solution that analyses user software requirements and provides viable suggestions to the user regarding their service. Previously, CORDULA chatbot was developed to analyze the software requirements but cannot keep the conversation’s context. The Rasa framework is integrated with the knowledge base to solve the issue, the knowledge base provides domain-specific knowledge to the chatbot. The software description is passed through the natural language understanding process to give consciousness to the chatbot. This process involves various machine learning models, including app family classification, to correctly identify the domain for user OTF service. The statistical models like naïve Bayes, kNN and SVM are compared with transformer models for this classification task. Furthermore, the entities (functional requirements) are also separated from the user description. The chatbot provides the suggestion of requirements from the preliminary service template with the support of the knowledge base. Furthermore, the generated response is compared with the state-of-the-art DialoGPT transformer model and ChatterBot conversational library. These models are trained over the software development related conversational dataset. All the responses are ranked using the DialoRPT model, and the BLEU score to evaluates the models’ responses. Moreover, the chatbot mod- els are tested with human participants, they used and scored the chatbot responses based on effectiveness, efficiency and satisfaction. The overall response accuracy is also measured by averaging the user approval over the generated responses. AU - Ahmed, Mobeen ID - 29000 TI - Knowledge Base Enhanced & User-centric Dialogue Design for OTF Computing ER - TY - GEN AU - Palushi, Juela ID - 45790 TI - Domain-aware Text Professionalization using Sequence-to-Sequence Neural Networks ER - TY - GEN AU - Budanurmath, Vinaykumar ID - 45789 TI - Propaganda Technique Detection Using Connotation Frames ER - TY - CONF AU - Dongol, Brijesh AU - Schellhorn, Gerhard AU - Wehrheim, Heike ED - Klin, Bartek ED - Lasota, Slawomir ED - Muscholl, Anca ID - 45248 T2 - 33rd International Conference on Concurrency Theory, CONCUR 2022, September 12-16, 2022, Warsaw, Poland TI - Weak Progressive Forward Simulation Is Necessary and Sufficient for Strong Observational Refinement VL - 243 ER - TY - CONF AB - In recent years, we observe an increasing amount of software with machine learning components being deployed. This poses the question of quality assurance for such components: how can we validate whether specified requirements are fulfilled by a machine learned software? Current testing and verification approaches either focus on a single requirement (e.g., fairness) or specialize on a single type of machine learning model (e.g., neural networks). In this paper, we propose property-driven testing of machine learning models. Our approach MLCheck encompasses (1) a language for property specification, and (2) a technique for systematic test case generation. The specification language is comparable to property-based testing languages. Test case generation employs advanced verification technology for a systematic, property dependent construction of test suites, without additional user supplied generator functions. We evaluate MLCheck using requirements and data sets from three different application areas (software discrimination, learning on knowledge graphs and security). Our evaluation shows that despite its generality MLCheck can even outperform specialised testing approaches while having a comparable runtime AU - Sharma, Arnab AU - Demir, Caglar AU - Ngonga Ngomo, Axel-Cyrille AU - Wehrheim, Heike ID - 28350 T2 - Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA) TI - MLCHECK–Property-Driven Testing of Machine Learning Classifiers ER - TY - CONF AB - Content is the new oil. Users consume billions of terabytes a day while surfing on news sites or blogs, posting on social media sites, and sending chat messages around the globe. While content is heterogeneous, the dominant form of web content is text. There are situations where more diversity needs to be introduced into text content, for example, to reuse it on websites or to allow a chatbot to base its models on the information conveyed rather than of the language used. In order to achieve this, paraphrasing techniques have been developed: One example is Text spinning, a technique that automatically paraphrases text while leaving the intent intact. This makes it easier to reuse content, or to change the language generated by the bot more human. One method for modifying texts is a combination of translation and back-translation. This paper presents NATTS, a naive approach that uses transformer-based translation models to create diversified text, combining translation steps in one model. An advantage of this approach is that it can be fine-tuned and handle technical language. AU - Bäumer, Frederik Simon AU - Kersting, Joschka AU - Denisov, Sergej AU - Geierhos, Michaela ID - 26049 KW - Software Requirements KW - Natural Language Processing KW - Transfer Learning KW - On-The-Fly Computing T2 - PROCEEDINGS OF THE INTERNATIONAL CONFERENCES ON WWW/INTERNET 2021 AND APPLIED COMPUTING 2021 TI - IN OTHER WORDS: A NAIVE APPROACH TO TEXT SPINNING ER - TY - THES AB - Previous research in proof-carrying hardware has established the feasibility and utility of the approach, and provided a concrete solution for employing it for the certification of functional equivalence checking against a specification, but fell short in connecting it to state-of-the-art formal verification insights, methods and tools. Due to the immense complexity of modern circuits, and verification challenges such as the state explosion problem for sequential circuits, this restriction of readily-available verification solutions severely limited the applicability of the approach in wider contexts. This thesis closes the gap between the PCH approach and current advances in formal hardware verification, provides methods and tools to express and certify a wide range of circuit properties, both functional and non-functional, and presents for the first time prototypes in which circuits that are implemented on actual reconfigurable hardware are verified with PCH methods. Using these results, designers can now apply PCH to establish trust in more complex circuits, by using more diverse properties which they can express using modern, efficient property specification techniques. AU - Wiersema, Tobias ID - 26746 KW - Proof-Carrying Hardware KW - Formal Verification KW - Sequential Circuits KW - Non-Functional Properties KW - Functional Properties TI - Guaranteeing Properties of Reconfigurable Hardware Circuits with Proof-Carrying Hardware ER - TY - JOUR AB - Due to the lack of established real-world benchmark suites for static taint analyses of Android applications, evaluations of these analyses are often restricted and hard to compare. Even in evaluations that do use real-world apps, details about the ground truth in those apps are rarely documented, which makes it difficult to compare and reproduce the results. To push Android taint analysis research forward, this paper thus recommends criteria for constructing real-world benchmark suites for this specific domain, and presents TaintBench, the first real-world malware benchmark suite with documented taint flows. TaintBench benchmark apps include taint flows with complex structures, and addresses static challenges that are commonly agreed on by the community. Together with the TaintBench suite, we introduce the TaintBench framework, whose goal is to simplify real-world benchmarking of Android taint analyses. First, a usability test shows that the framework improves experts’ performance and perceived usability when documenting and inspecting taint flows. Second, experiments using TaintBench reveal new insights for the taint analysis tools Amandroid and FlowDroid: (i) They are less effective on real-world malware apps than on synthetic benchmark apps. (ii) Predefined lists of sources and sinks heavily impact the tools’ accuracy. (iii) Surprisingly, up-to-date versions of both tools are less accurate than their predecessors. AU - Luo, Linghui AU - Pauck, Felix AU - Piskachev, Goran AU - Benz, Manuel AU - Pashchenko, Ivan AU - Mory, Martin AU - Bodden, Eric AU - Hermann, Ben AU - Massacci, Fabio ID - 27045 JF - Empirical Software Engineering SN - 1382-3256 TI - TaintBench: Automatic real-world malware benchmarking of Android taint analyses ER - TY - JOUR AB - Automated machine learning (AutoML) supports the algorithmic construction and data-specific customization of machine learning pipelines, including the selection, combination, and parametrization of machine learning algorithms as main constituents. Generally speaking, AutoML approaches comprise two major components: a search space model and an optimizer for traversing the space. Recent approaches have shown impressive results in the realm of supervised learning, most notably (single-label) classification (SLC). Moreover, first attempts at extending these approaches towards multi-label classification (MLC) have been made. While the space of candidate pipelines is already huge in SLC, the complexity of the search space is raised to an even higher power in MLC. One may wonder, therefore, whether and to what extent optimizers established for SLC can scale to this increased complexity, and how they compare to each other. This paper makes the following contributions: First, we survey existing approaches to AutoML for MLC. Second, we augment these approaches with optimizers not previously tried for MLC. Third, we propose a benchmarking framework that supports a fair and systematic comparison. Fourth, we conduct an extensive experimental study, evaluating the methods on a suite of MLC problems. We find a grammar-based best-first search to compare favorably to other optimizers. AU - Wever, Marcel Dominik AU - Tornede, Alexander AU - Mohr, Felix AU - Hüllermeier, Eyke ID - 21004 JF - IEEE Transactions on Pattern Analysis and Machine Intelligence KW - Automated Machine Learning KW - Multi Label Classification KW - Hierarchical Planning KW - Bayesian Optimization SN - 0162-8828 TI - AutoML for Multi-Label Classification: Overview and Empirical Evaluation ER - TY - JOUR AB - Automated Machine Learning (AutoML) seeks to automatically find so-called machine learning pipelines that maximize the prediction performance when being used to train a model on a given dataset. One of the main and yet open challenges in AutoML is an effective use of computational resources: An AutoML process involves the evaluation of many candidate pipelines, which are costly but often ineffective because they are canceled due to a timeout. In this paper, we present an approach to predict the runtime of two-step machine learning pipelines with up to one pre-processor, which can be used to anticipate whether or not a pipeline will time out. Separate runtime models are trained offline for each algorithm that may be used in a pipeline, and an overall prediction is derived from these models. We empirically show that the approach increases successful evaluations made by an AutoML tool while preserving or even improving on the previously best solutions. AU - Mohr, Felix AU - Wever, Marcel Dominik AU - Tornede, Alexander AU - Hüllermeier, Eyke ID - 21092 JF - IEEE Transactions on Pattern Analysis and Machine Intelligence TI - Predicting Machine Learning Pipeline Runtimes in the Context of Automated Machine Learning ER - TY - CONF AU - Tornede, Tanja AU - Tornede, Alexander AU - Wever, Marcel Dominik AU - Hüllermeier, Eyke ID - 21570 T2 - Proceedings of the Genetic and Evolutionary Computation Conference TI - Coevolution of Remaining Useful Lifetime Estimation Pipelines for Automated Predictive Maintenance ER - TY - CHAP AB - This chapter concentrates on aspect-based sentiment analysis, a form of opinion mining where algorithms detect sentiments expressed about features of products, services, etc. We especially focus on novel approaches for aspect phrase extraction and classification trained on feature-rich datasets. Here, we present two new datasets, which we gathered from the linguistically rich domain of physician reviews, as other investigations have mainly concentrated on commercial reviews and social media reviews so far. To give readers a better understanding of the underlying datasets, we describe the annotation process and inter-annotator agreement in detail. In our research, we automatically assess implicit mentions or indications of specific aspects. To do this, we propose and utilize neural network models that perform the here-defined aspect phrase extraction and classification task, achieving F1-score values of about 80% and accuracy values of more than 90%. As we apply our models to a comparatively complex domain, we obtain promising results. AU - Kersting, Joschka AU - Geierhos, Michaela ED - Loukanova, Roussanka ID - 17905 T2 - Natural Language Processing in Artificial Intelligence -- NLPinAI 2020 TI - Towards Aspect Extraction and Classification for Opinion Mining with Deep Sequence Networks VL - 939 ER - TY - GEN AU - Schott, Stefan ID - 22304 TI - Android App Analysis Benchmark Case Generation ER - TY - CONF AU - Hüllermeier, Eyke AU - Mohr, Felix AU - Tornede, Alexander AU - Wever, Marcel Dominik ID - 22913 TI - Automated Machine Learning, Bounded Rationality, and Rational Metareasoning ER - TY - CONF AU - Derrick, John AU - Doherty, Simon AU - Dongol, Brijesh AU - Schellhorn, Gerhard AU - Wehrheim, Heike ID - 22927 T2 - Proceedings of the 35th International Symposium on Distributed Computing (DISC) TI - On Strong Observational Refinement and Forward Simulation ER - TY - CONF AU - Kersting, Joschka AU - Geierhos, Michaela ID - 22051 T2 - Proceedings of the 10th International Conference on Data Science, Technology and Applications (DATA 2021) TI - Well-being in Plastic Surgery: Deep Learning Reveals Patients' Evaluations ER - TY - CONF AU - Witschen, Linus Matthias AU - Wiersema, Tobias AU - Raeisi Nafchi, Masood AU - Bockhorn, Arne AU - Platzner, Marco ED - Hannig, Frank ED - Derrien, Steven ED - Diniz, Pedro ED - Chillet, Daniel ID - 21953 T2 - Proceedings of International Symposium on Applied Reconfigurable Computing (ARC'21) TI - Timing Optimization for Virtual FPGA Configurations ER - TY - CONF AB - Static analysis is used to automatically detect bugs and security breaches, and aids compileroptimization. Whole-program analysis (WPA) can yield high precision, however causes long analysistimes and thus does not match common software-development workflows, making it often impracticalto use for large, real-world applications.This paper thus presents the design and implementation ofModAlyzer, a novel static-analysisapproach that aims at accelerating whole-program analysis by making the analysis modular andcompositional. It shows how to computelossless, persisted summaries for callgraph, points-to anddata-flow information, and it reports under which circumstances this function-level compositionalanalysis outperforms WPA.We implementedModAlyzeras an extension to LLVM and PhASAR, and applied it to 12 real-world C and C++ applications. At analysis time,ModAlyzermodularly and losslessly summarizesthe analysis effect of the library code those applications share, hence avoiding its repeated re-analysis.The experimental results show that the reuse of these summaries can save, on average, 72% ofanalysis time over WPA. Moreover, because it is lossless, the module-wise analysis fully retainsprecision and recall. Surprisingly, as our results show, it sometimes even yields precision superior toWPA. The initial summary generation, on average, takes about 3.67 times as long as WPA. AU - Schubert, Philipp AU - Hermann, Ben AU - Bodden, Eric ID - 21598 T2 - European Conference on Object-Oriented Programming (ECOOP) TI - Lossless, Persisted Summarization of Static Callgraph, Points-To and Data-Flow Analysis ER -