Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS

Filters

1
Reset filters

Settings
Now showing 1 - 10 of 1540
  • Publication
    Anonymization of German financial documents using neural network-based language models with contextual word representations
    ( 2022-03)
    Biesner, David
    ;
    Ramamurthy, Rajkumar
    ;
    Loitz, Rüdiger
    ;
    Lübbering, Max
    ;
    Hillebrand, Lars Patrick
    ;
    Ladi, Anna
    ;
    Stenzel, Robin
    ;
    Pielka, Maren
    ;
    Bauckhage, Christian
    ;
    Sifa, Rafet
    The automatization and digitalization of business processes have led to an increase in the need for efficient information extraction from business documents. However, financial and legal documents are often not utilized effectively by text processing or machine learning systems, partly due to the presence of sensitive information in these documents, which restrict their usage beyond authorized parties and purposes. To overcome this limitation, we develop an anonymization method for German financial and legal documents using state-of-the-art natural language processing methods based on recurrent neural nets and transformer architectures. We present a web-based application to anonymize financial documents and a large-scale evaluation of different deep learning techniques.
  • Publication
    Benchmarking table recognition performance on biomedical literature on neurological disorders
    ( 2022)
    Adams, Tim
    ;
    Namysl, Marcin
    ;
    Kodamullil, Alpha Tom
    ;
    Behnke, Sven
    ;
    Jacobs, Marc
    Table recognition systems are widely used to extract and structure quantitative information from the vast amount of documents that are increasingly available from different open sources. While many systems already perform well on tables with a simple layout, tables in the biomedical domain are often much more complex. Benchmark and training data for such tables are however very limited. To address this issue, we present a novel, highly curated benchmark dataset based on a hand-curated literature corpus on neurological disorders, which can be used to tune and evaluate table extraction applications for this challenging domain. We evaluate several state-of-the-art table extraction systems based on our proposed benchmark and discuss challenges that emerged during the benchmark creation as well as factors that can impact the performance of recognition methods. For the evaluation procedure, we propose a new metric as well as several improvements that result in a better performance evaluation. The resulting benchmark dataset (https://zenodo.org/record/5549977) as well as the source code to our novel evaluation approach can be openly accessed. Supplementary data are available at Bioinformatics online.
  • Publication
    Some applications of heat flow to Laplace eigenfunctions
    ( 2022)
    Georgiev, Bogdan
    ;
    Mukherjee, M.
    We consider mass concentration properties of Laplace eigenfunctions fl, that is, smooth functions satisfying the equation -Dfl=lfl, on a smooth closed Riemannian manifold. Using a heat diffusion technique, we first discuss mass concentration/localization properties of eigenfunctions around their nodal sets. Second, we discuss the problem of avoided crossings and (non)existence of nodal domains which continue to be thin over relatively long distances. Further, using the above techniques, we discuss the decay of Laplace eigenfunctions on Euclidean domains which have a central "thick" part and "thin" elongated branches representing tunnels of sub-wavelength opening. Finally, in an Appendix, we record some new observations regarding sub-level sets of the eigenfunctions and interactions of different level sets.
  • Publication
    Bringing Light Into the Dark: A large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
    ( 2022)
    Ali, Mehdi
    ;
    Berrendorf, Max
    ;
    Hoyt, Charles Tapley
    ;
    Vermue, Laurent
    ;
    Galkin, Mikhail
    ;
    Sharifzadeh, Sahand
    ;
    Fischer, Asja
    ;
    Tresp, Volker
    ;
    Lehmann, Jens
    The heterogeneity in recently published knowledge graph embedding models' implementations, training, and evaluation has made fair and thorough comparisons difficult. To assess the reproducibility of previously published results, we re-implemented and evaluated 21 models in the PyKEEN software package. In this paper, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all, as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 24,804 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and w here improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model's performance and is not only determined by its architecture. We provide evidence that several architectures can obtain results competitive to the state of the art when configured carefully. We have made all code, experimental configurations, results, and analyses available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking.
  • Publication
    A hybrid approach unveils drug repurposing candidates targeting an Alzheimer pathophysiology mechanism
    ( 2022)
    Lage-Rupprecht, Vanessa
    ;
    Schultz, Bruce
    ;
    Dick, Justus
    ;
    Namysl, Marcin
    ;
    Zaliani, Andrea
    ;
    Gebel, Stephan
    ;
    Pless, Ole
    ;
    Reinshagen, Jeanette
    ;
    Ellinger, Bernhard
    ;
    Ebeling, Christian
    ;
    Esser, Alexander
    ;
    Jacobs, Marc
    ;
    Claussen, Carsten
    ;
    Hofmann-Apitius, Martin
    The high number of failed pre-clinical and clinical studies for compounds targeting Alzheimer disease (AD) has demonstrated that there is a need to reassess existing strategies. Here, we pursue a holistic, mechanism-centric drug repurposing approach combining computational analytics and experimental screening data. Based on this integrative workflow, we identified 77 druggable modifiers of tau phosphorylation (pTau). One of the upstream modulators of pTau, HDAC6, was screened with 5,632 drugs in a tau-specific assay, resulting in the identification of 20 repurposing candidates. Four compounds and their known targets were found to have a link to AD-specific genes. Our approach can be applied to a variety of AD-associated pathophysiological mechanisms to identify more repurposing candidates.
  • Publication
    An Optimization for Convolutional Network Layers Using the Viola-Jones Framework and Ternary Weight Networks
    ( 2021-12-09)
    Agombar, Rhys
    ;
    Bauckhage, Christian
    ;
    Lübbering, Max
    ;
    Sifa, Rafet
    Neural networks have the potential to be extremely powerful for computer vision related tasks, but can be computationally expensive. Classical methods, by comparison, tend to be relatively light weight, albeit not as powerful. In this paper, we propose a method of combining parts from a classical system, called the Viola-Jones Object Detection Framework, with a modern ternary neural network to improve the efficiency of a convolutional neural net by replacing convolutional filters with a set of custom ones inspired by the framework. This reduces the number of operations needed for computing feature values with negligible effects on overall accuracy, allowing for a more optimized network.
  • Publication
    Decoupling Autoencoders for Robust One-vs-Rest Classification
    ( 2021-10-20)
    Lübbering, Max
    ;
    Gebauer, Michael
    ;
    Ramamurthy, Rajkumar
    ;
    Bauckhage, Christian
    ;
    Sifa, Rafet
    One-vs-Rest (OVR) classification aims to distinguish a single class of interest from other classes. The concept of novelty detection and robustness to dataset shift becomes crucial in OVR when the scope of the rest class extends from the classes observed during training to unseen and possibly unrelated classes. In this work, we propose a novel architecture, namely Decoupling Autoencoder (DAE) to tackle the common issue of robustness w.r.t. out-of-distribution samples which is prevalent in classifiers such as multi-layer perceptrons (MLP) and ensemble architectures. Experiments on plain classification, outlier detection, and dataset shift tasks show DAE to achieve robust performance across these tasks compared to the baselines, which tend to fail completely, when exposed to dataset shift. W hile DAE and the baselines yield rather uncalibrated predictions on the outlier detection and dataset shift task, we found that DAE calibration is more stable across all tasks. Therefore, calibration measures applied to the classification task could also improve the calibration of the outlier detection and dataset shift scenarios for DAE.
  • Publication
    Learning Weakly Convex Sets in Metric Spaces
    ( 2021-09-10)
    Stadtländer, Eike
    ;
    Horvath, Tamas
    ;
    Wrobel, Stefan
    We introduce the notion of weak convexity in metric spaces, a generalization of ordinary convexity commonly used in machine learning. It is shown that weakly convex sets can be characterized by a closure operator and have a unique decomposition into a set of pairwise disjoint connected blocks. We give two generic efficient algorithms, an extensional and an intensional one for learning weakly convex concepts and study their formal properties. Our experimental results concerning vertex classification clearly demonstrate the excellent predictive performance of the extensional algorithm. Two non-trivial applications of the intensional algorithm to polynomial PAC-learnability are presented. The first one deals with learning k-convex Boolean functions, which are already known to be efficiently PAC-learnable. It is shown how to derive this positive result in a fairly easy way by the generic intensional algorithm. The second one is concerned with the Euclidean space equipped with the Manhattan distance. For this metric space, weakly convex sets form a union of pairwise disjoint axis-aligned hyperrectangles. We show that a weakly convex set that is consistent with a set of examples and contains a minimum number of hyperrectangles can be found in polynomial time. In contrast, this problem is known to be NP-complete if the hyperrectangles may be overlapping.
  • Publication
    Vom Textgenerator zum digitalen Experten
    ( 2021-09-08)
    Paaß, Gerhard
    ;
    Hecker, Dirk
    Neue Sprachprogramme wie GPT-3 geben Maschinen nicht nur ein menschenähnliches Sprachgefühl, sondern sollen sie zugleich zu Fachleuten machen können. Was steckt dahinter? Und kann das gelingen?
  • Publication
    Advances in Password Recovery Using Generative Deep Learning Techniques
    ( 2021-09-07)
    Biesner, David
    ;
    Cvejoski, Kostadin
    ;
    Georgiev, Bogdan
    ;
    Sifa, Rafet
    ;
    Krupicka, Erik
    Password guessing approaches via deep learning have recently been investigated with significant breakthroughs in their ability to generate novel, realistic password candidates. In the present work we study a broad collection of deep learning and probabilistic based models in the light of password guessing: attention-based deep neural networks, autoencoding mechanisms and generative adversarial networks. We provide novel generative deep-learning models in terms of variational autoencoders exhibiting state-of-art sampling performance, yielding additional latent-space features such as interpolations and targeted sampling. Lastly, we perform a thorough empirical analysis in a unified controlled framework over well-known datasets (RockYou, LinkedIn, MySpace, Youku, Zomato, Pwnd). Our results not only identify the most promising schemes driven by deep neural networks, but also illustrate the strengths of each approach in terms of generation variability and sample uniqueness.