@inproceedings{32591,
  author       = {{Richter, Cedric and Wehrheim, Heike}},
  booktitle    = {{2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR)}},
  pages        = {{418--422}},
  title        = {{{TSSB-3M: Mining single statement bugs at massive scale}}},
  doi          = {{10.1145/3524842.3528505}},
  year         = {{2022}},
}

@inproceedings{31806,
  abstract     = {{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}},
  author       = {{Dreßler, Kevin and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}},
  booktitle    = {{Proceedings of the 33rd ACM Conference on Hypertext and Hypermedia}},
  keywords     = {{2022 RAKI SFB901 deer dice kevin knowgraphs limes ngonga sherif simba}},
  location     = {{Barcelona (Spain)}},
  title        = {{{ADAGIO - Automated Data Augmentation of Knowledge Graphs Using Multi-expression Learning}}},
  doi          = {{10.1145/3511095.3531287}},
  year         = {{2022}},
}

@inproceedings{33274,
  author       = {{Chen, Wei-Fan and Chen, Mei-Hua and Mudgal, Garima and Wachsmuth, Henning}},
  booktitle    = {{Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022)}},
  pages        = {{51 -- 61}},
  title        = {{{Analyzing Culture-Specific Argument Structures in Learner Essays}}},
  year         = {{2022}},
}

@inbook{32179,
  abstract     = {{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.}},
  author       = {{Kersting, Joschka and Ahmed, Mobeen and Geierhos, Michaela}},
  booktitle    = {{HCI International 2022 Posters}},
  editor       = {{Stephanidis, Constantine and Antona, Margherita and Ntoa, Stavroula}},
  isbn         = {{9783031064166}},
  issn         = {{1865-0929}},
  keywords     = {{On-The-Fly Computing, Chatbot, Knowledge Base}},
  location     = {{Virtual}},
  pages        = {{419----426}},
  publisher    = {{Springer International Publishing}},
  title        = {{{Chatbot-Enhanced Requirements Resolution for Automated Service Compositions}}},
  doi          = {{10.1007/978-3-031-06417-3_56}},
  volume       = {{1580}},
  year         = {{2022}},
}

@inproceedings{31054,
  abstract     = {{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.}},
  author       = {{Kersting, Joschka and Bäumer, Frederik Simon}},
  booktitle    = {{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}},
  editor       = {{Kersting, Joschka}},
  keywords     = {{Sentiment analysis, Natural language processing, Aspect phrase extraction}},
  location     = {{Barcelona, Spain}},
  pages        = {{5--9}},
  publisher    = {{IARIA}},
  title        = {{{Implicit Statements in Healthcare Reviews: A Challenge for Sentiment Analysis}}},
  year         = {{2022}},
}

@inproceedings{31068,
  author       = {{Chen, Mei-Hua and Mudgal, Garima and Chen, Wei-Fan and Wachsmuth, Henning}},
  booktitle    = {{EUROCALL}},
  title        = {{{Investigating the argumentation structures of EFL learners from diverse language backgrounds}}},
  year         = {{2022}},
}

@misc{33033,
  author       = {{Fehring, Lukas}},
  title        = {{{Combined Ranking and Regression Trees for Algorithm Selection}}},
  year         = {{2022}},
}

@unpublished{30867,
  abstract     = {{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.}},
  author       = {{Tornede, Alexander and Bengs, Viktor and Hüllermeier, Eyke}},
  booktitle    = {{Proceedings of the 36th AAAI Conference on Artificial Intelligence}},
  publisher    = {{AAAI}},
  title        = {{{Machine Learning for Online Algorithm Selection under Censored Feedback}}},
  year         = {{2022}},
}

@unpublished{30865,
  abstract     = {{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.}},
  author       = {{Tornede, Alexander and Gehring, Lukas and Tornede, Tanja and Wever, Marcel Dominik and Hüllermeier, Eyke}},
  booktitle    = {{Machine Learning}},
  title        = {{{Algorithm Selection on a Meta Level}}},
  year         = {{2022}},
}

@article{33090,
  abstract     = {{<jats:title>Abstract</jats:title><jats:p>Heated 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.</jats:p>}},
  author       = {{Gevers, Karina and Tornede, Alexander and Wever, Marcel Dominik and Schöppner, Volker and Hüllermeier, Eyke}},
  issn         = {{0043-2288}},
  journal      = {{Welding in the World}},
  keywords     = {{Metals and Alloys, Mechanical Engineering, Mechanics of Materials}},
  publisher    = {{Springer Science and Business Media LLC}},
  title        = {{{A comparison of heuristic, statistical, and machine learning methods for heated tool butt welding of two different materials}}},
  doi          = {{10.1007/s40194-022-01339-9}},
  year         = {{2022}},
}

@proceedings{53803,
  editor       = {{Kersting, Joschka}},
  location     = {{Barcelona, Spain}},
  publisher    = {{IARIA}},
  title        = {{{PATTERNS 2022 The Fourteenth International Conferences on Pervasive Patterns and Applications}}},
  year         = {{2022}},
}

@phdthesis{34041,
  author       = {{Witschen, Linus Matthias}},
  title        = {{{Frameworks and Methodologies for Search-based Approximate Logic Synthesis}}},
  doi          = {{10.17619/UNIPB/1-1649}},
  year         = {{2022}},
}

@inproceedings{32342,
  author       = {{Ahmed, Qazi Arbab and Platzner, Marco}},
  location     = {{Pafos, Cyprus}},
  publisher    = {{IEEE Computer Society Annual Symposium on VLSI (ISVLSI,2022)}},
  title        = {{{On the Detection and Circumvention of Bitstream-Level Trojans in FPGAs}}},
  year         = {{2022}},
}

@misc{29000,
  abstract     = {{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.}},
  author       = {{Ahmed, Mobeen}},
  title        = {{{Knowledge Base Enhanced & User-centric Dialogue Design for OTF Computing}}},
  year         = {{2022}},
}

@misc{45790,
  author       = {{Palushi, Juela}},
  title        = {{{Domain-aware Text Professionalization using Sequence-to-Sequence Neural Networks}}},
  year         = {{2022}},
}

@misc{45789,
  author       = {{Budanurmath, Vinaykumar}},
  title        = {{{Propaganda Technique Detection Using Connotation Frames}}},
  year         = {{2022}},
}

@inproceedings{45248,
  author       = {{Dongol, Brijesh and Schellhorn, Gerhard and Wehrheim, Heike}},
  booktitle    = {{33rd International Conference on Concurrency Theory, CONCUR 2022, September 12-16, 2022, Warsaw, Poland}},
  editor       = {{Klin, Bartek and Lasota, Slawomir and Muscholl, Anca}},
  pages        = {{31:1–31:23}},
  publisher    = {{Schloss Dagstuhl - Leibniz-Zentrum für Informatik}},
  title        = {{{Weak Progressive Forward Simulation Is Necessary and Sufficient for Strong Observational Refinement}}},
  doi          = {{10.4230/LIPIcs.CONCUR.2022.31}},
  volume       = {{243}},
  year         = {{2022}},
}

@article{30511,
  abstract     = {{<jats:title>Abstract</jats:title><jats:p>Many 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 <jats:sc>VarAlyzer</jats:sc>, a novel static analysis approach for software product lines. <jats:sc>VarAlyzer</jats:sc> 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. <jats:sc>VarAlyzer</jats:sc> ’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 <jats:sc>VarAlyzer</jats:sc> 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.</jats:p>}},
  author       = {{Schubert, Philipp and Gazzillo, Paul and Patterson, Zach and Braha, Julian and Schiebel, Fabian Benedikt and Hermann, Ben and Wei, Shiyi and Bodden, Eric}},
  issn         = {{0928-8910}},
  journal      = {{Automated Software Engineering}},
  keywords     = {{inter-procedural static analysis, software product lines, preprocessor, LLVM, C/C++}},
  number       = {{1}},
  publisher    = {{Springer Science and Business Media LLC}},
  title        = {{{Static data-flow analysis for software product lines in C}}},
  doi          = {{10.1007/s10515-022-00333-1}},
  volume       = {{29}},
  year         = {{2022}},
}

@inproceedings{28350,
  abstract     = {{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}},
  author       = {{Sharma, Arnab and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille and Wehrheim, Heike}},
  booktitle    = {{Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}},
  publisher    = {{IEEE}},
  title        = {{{MLCHECK–Property-Driven Testing of Machine Learning Classifiers}}},
  year         = {{2021}},
}

@inproceedings{26049,
  abstract     = {{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.}},
  author       = {{Bäumer, Frederik Simon and Kersting, Joschka and Denisov, Sergej and Geierhos, Michaela}},
  booktitle    = {{PROCEEDINGS OF THE INTERNATIONAL CONFERENCES ON WWW/INTERNET 2021 AND APPLIED COMPUTING 2021}},
  keywords     = {{Software Requirements, Natural Language Processing, Transfer Learning, On-The-Fly Computing}},
  location     = {{Lisbon, Portugal}},
  pages        = {{221----225}},
  publisher    = {{IADIS}},
  title        = {{{IN OTHER WORDS: A NAIVE APPROACH TO TEXT SPINNING}}},
  year         = {{2021}},
}