- informatik-vortraege - lists.rwth-aachen.de

von Obster, Mathias

+********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * +********************************************************************** Zeit: Dienstag, 10. November 2020, 14:00 Uhr Ort: Videokonferenz (Zoom-Meeting, Informationen siehe unten) Referent: Mathias Obster, M.Sc. RWTH Informatik 11 - Embedded Software Thema: Unterstützung der SPS-Programmierung durch Statische Analyse während der Programmeingabe Abstract: Durch abstrakte Interpretation und genauer durch Wertemengenanalyse lassen sich vollautomatisch Fehler in Programmcode finden, ohne diesen auszuführen. Bei Programmen für Speicherprogrammierbare Steuerungen (SPSen) ist dies für die Fehlervermeidung von besonderem Interesse, da sie im industriellen Umfeld zum Einsatz kommen. In diesem Vortrag wird ein Ansatz vorgestellt, mit dem diese Methoden bereits während der Programmeingabe, also während der Entwicklung eines SPS-Programms, zur Fehlererkennung und -vermeidung beitragen kann. Dafür wurde das Analyseframework ARCADE.PLC erweitert, sodass es Analyseergebnisse in einer Entwicklungsumgebung darstellen kann, die auch in der Industrie zum Einsatz kommt. So können dort sowohl Warnungen vor potenziell fehlerhaftem Programmverhalten als auch mögliche Variablenwerte dargestellt werden. Ein neu eingeführter inkrementeller Ansatz kann darüber hinaus den Berechnungsaufwand verringern, der sonst durch die häufige Ausführung der Analysen entsteht. Dabei wird ausgenutzt, dass sich während der Entwicklung in kurzen Zeitintervallen üblicherweise nur kleine Änderungen für das Gesamtprogramm ergeben. Für die Bereitstellung einer integrierten Lösung für den Anwender wurden die Konzepte und eine Erweiterung für eine Entwicklungsumgebung für SPS-Programme prototypisch umgesetzt und im Rahmen einer kleinen Nutzerstudie evaluiert. Dabei stand die Frage im Mittelpunkt, ob Programmierer während der Eingabe und Bearbeitung eines SPS-Programms von Ergebnissen der Statischen Analyse profitieren können. Es laden ein: die Dozentinnen und Dozenten der Informatik ******************************** Thema: [Promotion Mathias Obster] Vortrag Uhrzeit: 10.Nov.2020 02:00 PM Amsterdam, Berlin, Rom, Stockholm, Wien Zoom-Meeting beitreten https://rwth.zoom.us/j/98589897540?pwd=OWZidEpuU1N5bjA5UFIxcFhNUEJidz09 Meeting-ID: 985 8989 7540 Kenncode: 111012

3 Jahre, 6 Monate

1
0
0 0

21.10., 10.00: Prof. Michael Schaub, RWTH Aachen: Learning from signals on graphs with unobserved edges

von Bolke-Hermanns, Helen

Dear members of the Computer Science Department, You are cordially invited to the talk of Prof. Michael Schaub, RWTH Aachen. Title: Learning from signals on graphs with unobserved edges Abstract: In many applications we are confronted with the following system identification scenario: we observe a dynamical process that describes the state of a system at particular times. Based on these observations we want to infer the (dynamical) interactions between the entities we observe. In the context of a distributed system, this typically corresponds to a "network identification" task: find the (weighted) edges of the graph of interconnections. However, often the number of samples we can obtain from such a process are far too few to identify the edges of the network exactly. Can we still reliably infer some aspects of the underlying system? Motivated by this question we consider the following identification problem: instead of trying to infer the exact network, we aim to recover a (low-dimensional) statistical model of the network based on the observed signals on the nodes. More concretely, here we focus on observations that consist of snapshots of a diffusive process that evolves over the unknown network. We model the (unobserved) network as generated from an independent draw from a latent stochastic blockmodel (SBM), and our goal is to infer both the partition of the nodes into blocks, as well as the parameters of this SBM. We present simple spectral algorithms that provably solve the partition and parameter inference problems with high-accuracy. We further discuss some possible variations and extensions of this problem setup. https://www.informatik.rwth-aachen.de/go/id/jgfsd Wednesday, 21.10.2020, 10:00 Join Zoom Meeting https://rwth.zoom.us/j/92047949381?pwd=LzIwUW96WEM0MkRjZ01FUmhwd1I3QT09<https://www.google.com/url?q=https://rwth.zoom.us/j/92047949381?pwd%3DLzIwU…> Meeting ID: 920 4794 9381 Password: unravel Best regards Helen Bolke-Hermanns Helen Bolke-Hermanns Fachgruppe Informatik RWTH Aachen University Ahornstr. 55, D-52074 Aachen Building E3, 2nd floor, Room 9218 Telefon: +49 (241) 80-21-004 Fax: +49 (241) 80-22 215 E-Mail: Helen.Bolke-Hermanns(a)Informatik.RWTH-Aachen.de<mailto:Helen.Bolke-Hermanns@Informatik.RWTH-Aachen.de> [rwth_informatik_bild_rgb]

3 Jahre, 6 Monate

1
0
0 0

7.10., 17.00: Guy Van den Broeck, UCLA: From Probabilistic Circuits to Probabilistic Programs and Back

von Bolke-Hermanns, Helen

Dear members of the Computer Science Department, You are cordially invited to the talk of the UnRAVeL guest Guy Van den Broeck, UCLA Title: From Probabilistic Circuits to Probabilistic Programs and Back Abstract: Probabilistic graphical models are a rich staple of probabilistic AI. However, they make a very specific choice of abstraction: probability distributions are represented by their variable-level (in)dependencies. In this talk I present some recent work on probabilistic models that go beyond classical PGMs, and make a radically different choice of abstraction; one that is computational. Concretely, I will discuss two classes of models: probabilistic circuits and probabilistic programs. Probabilistic circuits represent distributions through the computation graph of probabilistic inference. They move beyond PGMs by guaranteeing tractable inference for certain classes of queries. Probabilistic programs represent distributions through higher-level primitives of computation: iteration, branching, and procedural abstraction. They move beyond PGMs by looking "inside" of the dependencies. Finally, I will illustrate how these two computational abstractions are themselves closely related, by showing how the Dice probabilistic programming language compiles probabilistic programs into probabilistic circuits for inference. Wednesday, Oct. 7th, 5.00 pm The talk will take place as a zoom-session: https://rwth.zoom.us/j/92047949381?pwd=LzIwUW96WEM0MkRjZ01FUmhwd1I3QT09<https://www.google.com/url?q=https://rwth.zoom.us/j/92047949381?pwd%3DLzIwU…> Meeting ID: 920 4794 9381, Password: unravel Best regards Helen Bolke-Hermanns Helen Bolke-Hermanns Fachgruppe Informatik RWTH Aachen University Ahornstr. 55, D-52074 Aachen Building E3, 2nd floor, Room 9218 Telefon: +49 (241) 80-21-004 Fax: +49 (241) 80-22 215 E-Mail: Helen.Bolke-Hermanns(a)Informatik.RWTH-Aachen.de<mailto:Helen.Bolke-Hermanns@Informatik.RWTH-Aachen.de> [rwth_informatik_bild_rgb]

3 Jahre, 6 Monate

1
0
0 0

Einladung Informatik-Oberseminar Dr. Andreas Wortmann, 03. November 2020, 12:30 Uhr

von Bernhard Rumpe

********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * *********************************************************************** Zeit: Dienstag, 03. November 2020, 12:30 Uhr Zoom: https://rwth.zoom.us/j/92659511051?pwd=TmVibnlCNUdYZzlZSW52eCs0V2RjQT09 Referent: Dr. Andreas Wortmann Thema: Model-Driven Architecture and Behavior of Cyber-Physical Systems Vorstellung des Habilitationsvorhabens. Abstract: Systems engineering has produced striking results in many domains. Researchers and practitioners have devised concepts, methods, tools that autonomously move vehicles, enable doctors to conduct remote surgeries across continents, and sent astronauts into space. All of these cyber-physical systems are driven by software whose complexity increases tremendously. Overcompensating this growth in software and systems complexity demands novel methods that increase the abstraction in systems engineering, advance automation, and facilitate the integration of domain expert solutions. Model-based systems engineering aims to address this complexity by advancing systems engineering from its contemporary document-based processes to sophisticated model-based processes. In the latter, abstract models serve as means for systems design, communication, documentation, and basis for implementation. But to overcompensate the growth in complexity, using models as secondary artifacts is insufficient. Comprehensive research in software engineering has led to recognizing that model-driven processes, in which models are the primary engineering artifacts, can significantly improve abstraction, automation, and domain-specific modeling to address the increasing complexity in systems engineering. Yet, model-based systems engineering focuses on informal models that are hardly accessible to meaningful automation and overly generic. This thesis summarizes 14 selected publications of a research program towards a model-driven systems engineering that operates on domain-specific modeling languages, supports sophisticated modeling methods, and enables the systematic operation of cyber-physical systems. The results of this research program cover four substantial challenges towards the model-driven engineering of cyber-physical systems: First, it contributes to understanding the use of models and modeling languages for cyber-physical systems through two comprehensive literature studies on modeling for cyber-physical systems in Industry 4.0 and mobile robotics. The studies surveyed over 3.000 publications each and produced insights into requirements for the efficient model-driven engineering and operations of cyber-physical systems in both domains. Second, it conduces novel foundations for the efficient engineering of domain-specific modeling languages based on the requirements identified in both studies. These foundations introduce innovative notions of language components and their composition upon which families of domain-specific modeling languages can be created systematically efficiently. Third, it leverages these foundations to produce modeling languages to describe functional architectures and geometric-physical architectures of cyber-physical systems that support unprecedented automated modeling methods, including tracing, decomposition, and semantic differencing, to facilitate modeling, maintaining, and evolving these architectures. Fourth, it exploits the novel language engineering foundations and the unprecedented automated modeling methods to alleviate the systematic operation of cyber-physical systems with digital twins that represent and optimize the observed systems. Hence, this research program forges a bridge from observations on modeling cyber-physical systems, over software language engineering and modeling methods, to their operation that supports researchers and practitioners to advance from the contemporary document-based engineering of cyber-physical systems to their systematic model-driven engineering. Vita: Andreas Wortmann is a tenured research associate at the Chair for Software Engineering at RWTH Aachen University. There, he leads a team on model-driven systems engineering, coordinates a workstream of the Internet of Production excellence cluster, and advises the Center for Systems Engineering. He conducts research in model-driven software and systems engineering, formal methods in software engineering, and software language engineering, which is documented in over 70 publications. Moreover, he has chaired and organized various international conferences and workshops, serves on the board of the European Association for Programming Languages and Systems (EAPLS), and co-chairs the working group on model-based systems engineering of the German INCOSE chapter GfSE. Es laden ein: die Dozentinnen und Dozenten der Informatik -- ---------------------------------------------------------------- Prof. Dr. Bernhard Rumpe | http://www.se-rwth.de Lehrstuhl Software Engineering | Informatik 3 Ahornstr. 55, 52074 Aachen, Germany | RWTH Aachen University Phone ++49 241 80-21301 / Fax -22218 |

3 Jahre, 7 Monate

1
0
0 0

Einladung: Informatik Oberseminar Markus Hoehnerbach

von Markus Hoehnerbach

+********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * +********************************************************************** Zeit: Dienstag, 22. September 2020, 16.00 Uhr Ort: Videokonferenz (Zoom-Meeting, Informationen siehe unten) Referent: Markus Hoehnerbach M.Sc. High-Performance and Automatic Computing Thema: A Framework for the Vectorization of Molecular Dynamics Kernels Abstract: We introduce a domain-specific language (DSL) for many-body potentials, which are used in molecular dynamics (MD) simulations in the area of materials science. We also introduce a compiler to translate the DSL into high-performance code suitable for modern supercomputers. We begin by studying ways to speedup up potentials on supercomputers using two case studies: The Tersoff and the AIREBO potentials. In both case studies, we identify a number of optimizations, both domain-specific and general, to achieve speedups of up to 5x; we also introduce a method to keep the resulting code performance portable. During the AIREBO case study, we also discover that the existing code contains a number of errors. This experience motivates us to include the derivation step, the most error-prone step in manual optimization, in our automation effort. After having identified beneficial optimization techniques, we create a ``potential compiler'', short PotC, which generates fully-usable performance-portable potential implementations from specifications written in our DSL. DSL code is significantly shorter (20x to 30x) than a manual code, reducing both manual work and opportunities to introduce bugs. We present performance results on five different platforms: Three CPU platforms (Broadwell, Knights Landing, and Skylake) and two GPU platforms (Pascal and Volta). While the performance in some cases remains far below that of hand-written code, it also manages to match or exceed manually written implementations in other cases. For these cases, we achieve speedups of up to 9x compared to non-vectorized code. Es laden ein: die Dozentinnen und Dozenten der Informatik ******************************** Thema: Dissertation M. Höhnerbach Uhrzeit: 22.Sep.2020 03:45 PM Paris Zoom-Meeting beitreten https://rwth.zoom.us/j/98920238040?pwd=Q3F1OStEcklpcDV1Vk5IWEp0cFFEQT09 Meeting-ID: 989 2023 8040 Kenncode: 668020

3 Jahre, 7 Monate

1
0
0 0

Einladung Informatik-Oberseminar Jan Rüth

von Jan Rüth

+********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * +********************************************************************** Zeit: Freitag, 14. August 2020, 13.00 Uhr Zoom: https://rwth.zoom.us/j/94972202308?pwd=Y1o5cnBQYTYxdS9tYldaN0piQkozQT09 Referent: Jan Rüth, M.Sc. Lehrstuhl Informatik 4 Thema: Measuring the Evolution of the Internet in the Age of Giants Abstract: The Internet has evolved into an essential cornerstone of modern life. At its core, it is seemingly still powered by protocols developed in the late 1980s. Since then, the Internet has experienced a colossal visible evolution, e.g., from delivering small text files over dynamic websites to highly interactive and bulky content that define whole economic sectors. Notwithstanding, it is hard to believe that this change demanded no technological evolution, and in fact, research and industry have worked on many mechanisms and improvements to the core protocols. Today, we see Internet giants such as Google, Facebook, or Akamai controlling clients, servers, and networks driving these changes. Still, research has shown that these innovations often remain hard to deploy in practice as the Internet has condensed to supporting only a small set of protocols and parts of their features today. In this talk, we present novel Internet measurement methodologies to gain an understanding of how the Internet has evolved from textbook knowledge, how it deviates from standardized practices, and how these discovered discrepancies affect Internet operation. To this end, we recognize the critical role of Internet giants and specifically investigate their impact on core Internet technologies. In this presentation, we focus on the transport layer and examine TCP initial congestion window configurations, Congestion Control fairness, and QUIC as a new Internet transport. Lastly, we present how WebAssembly is largely abused for cryptocurrency mining in the Web today. Our contributions demonstrate that Internet giants coin practical Internet evolution. While they are keen to standardize their innovations, their configurations are often a well-kept secret. Their market dominance challenges the innovation of others, but even they are not immune to an abuse of their technology. Es laden ein: die Dozentinnen und Dozenten der Informatik

3 Jahre, 8 Monate

1
0
0 0

Einladung: Informatik-Oberseminar Frau Rihan Hai

von Leany Maaßen

+********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * +********************************************************************** Zeit: Montag, 13. Juli 2020, 16:00 Uhr Zoom: <https://rwth.zoom.us/j/95676455814?pwd=NUEvVnFVNEVLSjFsTWY2OEw2VWhrdz09> https://rwth.zoom.us/j/95676455814?pwd=NUEvVnFVNEVLSjFsTWY2OEw2VWhrdz09 Meeting-ID: 956 7645 5814 Passwort: 302988 Referentin: M.Eng. Rihan Hai Lehrstuhl Informatik 5 Thema: Data integration and Metadata Management in Data Lakes Abstract: Although big data has been discussed for some years, it still has many research challenges, such as the variety of data. Non-integrated data management systems with heterogeneous schemas, query languages, and data models result in information silos. As traditional 'schema-on-write' approaches such as data warehouses cannot solve the challenges to efficiently integrate, access, and query the information silos, data lake systems have been proposed as a solution to this problem. Data lakes are repositories storing raw data in its original format and providing a common access interface. In this thesis, we present a comprehensive and flexible data lake architecture and the prototype system Constance. First, we propose a native mapping representation to capture the hierarchical structures of nested mappings and efficient mapping generation algorithms. Second, to provide a unified querying interface, we design a novel query rewriting engine that combines logical methods for data integration based on declarative mappings with the big data processing system Apache Spark. Third, we also study the formalism of the generated schema mappings as dependencies. Our algorithmic approach transforms schema mappings expressed in second-order logic to their logically equivalent first-order forms. Finally, we introduce clustering-based algorithms to discover relaxed functional dependencies, which enrich the metadata and improve data quality in the data lake. Es laden ein: die Dozentinnen und Dozenten der Informatik _______________________________ Leany Maaßen RWTH Aachen University Lehrstuhl Informatik 5, LuFG Informatik 5 Prof. Dr. Stefan Decker, Prof. Dr. Matthias Jarke, Prof. Gerhard Lakemeyer Ph.D. Ahornstrasse 55 D-52074 Aachen Tel: 0241-80-21509 Fax: 0241-80-22321 E-Mail: maassen(a)dbis.rwth-aachen.de

3 Jahre, 10 Monate

1
0
0 0

Einladung: Informatik-Oberseminar Herr Markus Beutel

von Leany Maaßen

+********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * +********************************************************************** Zeit: Dienstag, 30. Juni 2020, 14.00-15.00 Uhr Zoom: <https://rwth.zoom.us/j/95676455814?pwd=NUEvVnFVNEVLSjFsTWY2OEw2VWhrdz09> https://rwth.zoom.us/j/95676455814?pwd=NUEvVnFVNEVLSjFsTWY2OEw2VWhrdz09 Meeting-ID: 956 7645 5814 Passwort: 302988 Referent: Dipl.-Kfm. Markus Beutel Thema: End-to-End-Integration von komplementären Mobilitätsdienstleistungen durch unternehmensübergreifende Anbieterkooperation Abstract: Reisenden steht heutzutage eine Vielzahl unterschiedlicher Verkehrsmodi zur Verfügung. Dabei können sich viele Fortbewegungsmittel aufgrund individueller Charakteristika gegenseitig ergänzen, anstatt sich zu substituieren. Durch eine zumindest in Teilen segmentierte und anbieterspezifische Bereitstellung von Verkehrsdienstleistungen können beispielsweise ökonomische und ökologische Ineffizienzen entstehen. Im Zentrum einer vollständigen Digitalisierung und Integration heterogener Mobilitätsdienstleistungen sollte daher der ganzheitliche Dienstleistungsprozess, über die gesamte Servicekette hinweg, in den Mittelpunkt gestellt werden. Das übergeordnete Ziel dieser Arbeit besteht in der Erforschung einer integrierten Bereitstellung sich ergänzender Mobilitätsdienstleistungen, über Unternehmensgrenzen hinweg. Ausgangspunkt dieser Arbeit bildet die Untersuchung einer spezifischen Mobilitätsplattform im Hinblick auf verschiedene Integrationsfaktoren. Auf Basis einer umfassenden Analyse von Mobilitätsplattformen und in Verbindung mit der Beschreibung eines organisatorischen Rollenmodells werden daraufhin mögliche Anbieterkooperationsszenarien beschrieben. Um die unternehmensübergreifende Integration auf Prozessebene zu betrachten, wird schließlich ein Ansatz zur Erweiterung eines Softwarewerkzeugs zur Fusion von Geschäftsprozessmodellen evaluiert. Es laden ein: die Dozentinnen und Dozenten der Informatik _______________________________ Leany Maaßen RWTH Aachen University Lehrstuhl Informatik 5, LuFG Informatik 5 Prof. Dr. Stefan Decker, Prof. Dr. Matthias Jarke, Prof. Gerhard Lakemeyer Ph.D. Ahornstrasse 55 D-52074 Aachen Tel: 0241-80-21509 Fax: 0241-80-22321 E-Mail: maassen(a)dbis.rwth-aachen.de

3 Jahre, 10 Monate

1
0
0 0

Einladung: Informatik-Oberseminar Herr István Koren

von Leany Maaßen

+********************************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * +********************************************************************** Zeit: Freitag, 08. Mai 2020, 11.00 Uhr Zoom: https://rwth.zoom.us/j/94637532047?pwd=aVlweVRLdGU0OWNjdEh4TmJhSktrUT09 Referent: Dipl.-Medieninf. István Koren Lehrstuhl Informatik 5 Thema: DevOpsUse: Community-Driven Continuous Innovation of Web Information Infrastructures Abstract: The steady evolution of the Web over the last thirty years was shaped by an interplay of new technologies and innovative applications. The current challenges are caused by the ongoing digital transformation of whole societies. In Industry 4.0 for example, these are changing workplace settings and the adoption of the Internet of Things. Inhibiting the demanded fast innovation cycles, this may create a disruptive and unstable environment in which the requirements of heterogeneous professional communities need to be addressed. Information systems infrastructure, while only partially visible and thus hard to grasp, has a strong influence on practices in professional communities. Therefore, our aim is to stabilize the dichotomies apparent in the Web by means of an agile information systems development methodology. It supports the evolution of infrastructure through community-driven and model-based technologies to guide it on a sustainable path of continuous innovation. Agile development practices in software engineering, in particular the already established DevOps approach, promote stronger cooperation between development and operating teams. Our DevOpsUse methodology additionally fosters a stronger involvement of end user communities in software development processes by including them in the process of infrastructuring, i.e. the appropriation of infrastructure during its usage. The developed DevOpsUse methodology has been successfully validated by the transitions between three generations of technologies: near real-time peer-to-peer Web architectures, edge computing, and the Internet of Things. In particular, we were able to demonstrate our methodologys capabilities through longitudinal studies in several large-scale international digitalization projects. Beyond Web information systems, the framework and its open source tools are applicable in further innovative areas like mixed reality. Its broad adaptability testifies that DevOpsUse has the potential to unlock sustainable innovation capabilities. Es laden ein: die Dozentinnen und Dozenten der Informatik _______________________________ Leany Maaßen RWTH Aachen University Lehrstuhl Informatik 5, LuFG Informatik 5 Prof. Dr. Stefan Decker, Prof. Dr. Matthias Jarke, Prof. Gerhard Lakemeyer Ph.D. Ahornstrasse 55 D-52074 Aachen Tel: 0241-80-21509 Fax: 0241-80-22321 E-Mail: maassen(a)dbis.rwth-aachen.de

4 Jahre

1
0
0 0

Einladung: Informatik-Oberseminar Kazuki Irie

von Sekretariat I6

****************************************************** * * * Einladung * * * * Informatik-Oberseminar * * * ******************************************************* Zeit: Dienstag, 05. Mai 2020, 14.00 Uhr Zoom: https://us02web.zoom.us/j/84813327259?pwd=Y2NydlRMRzE1dkpkcmpERkFwMWZYZz09 Referent: Kazuki Irie, M.Sc. Thema: Advancing Neural Language Modeling in Automatic Speech Recognition// Abstract: Statistical language modeling is one of the fundamental problems in natural language processing. In the recent years, language modeling has seen great advances by active research and engineering efforts in applying artificial neural networks, especially those which are recurrent. The application of neural language models to speech recognition has now become well established and ubiquitous. Despite this impression of some degree of maturity, we claim that the full potential of the neural network based language modeling is yet to be explored. In this thesis, we further advance neural language modeling in automatic speech recognition, by investigating a number of new perspectives. From the architectural view point, we investigate the newly proposed Transformer neural networks for language modeling application. The original model architecture proposed for machine translation is studied and modified to accommodate the specific task of language modeling. Particularly deep models with about one hundred layers are developed. We present an in-depth comparison with the state-of-the-art recurrent neural network language models based on the long short-term memory. While scaling up language modeling to larger scale datasets, the diversity of the data emerges as an opportunity and a challenge. The current state-of-the-art neural language modeling lacks a mechanism of handling diverse data from different domains for a single model to perform well across different domains. In this context, we introduce domain robust language modeling with neural networks, and propose two solutions. As a first solution, we propose a new type of adaptive mixture of experts model which is fully based on neural networks. In the second approach, we investigate knowledge distillation from multiple domain expert models, as a solution to the large model size problem seen in the first approach. Methods for practical applications of knowledge distillation to large vocabulary language modeling are proposed, and studied to a large extent. Finally, we investigate the potential of neural language models to leverage long-span cross-sentence contexts for cross-utterance speech recognition. The appropriate training method for such a scenario is under-explored in the existing works. We carry out systematic comparisons of the training methods, allowing us to achieve improvements in cross-utterance speech recognition. In the same context, we study the sequence length robustness for both recurrent neural networks based on the long short-term memory and Transformers, because such a robustness is one of the fundamental properties we wish to have, in neural networks with the ability to handle variable length contexts. Throughout the thesis, we tackle these problems through novel perspectives of neural language modeling, while keeping the traditional spirit of language modeling in speech recognition. Es laden ein: die Dozentinnen und Dozenten der Informatik -- -- Stephanie Jansen Faculty of Mathematics, Computer Science and Natural Sciences HLTPR - Human Language Technology and Pattern Recognition RWTH Aachen University Ahornstraße 55 D-52074 Aachen Tel. Frau Jansen: +49 241 80-216 06 Tel. Frau Andersen: +49 241 80-216 01 Fax: +49 241 80-22219 sek(a)i6.informatik.rwth-aachen.de www.hltpr.rwth-aachen.de Tel: +49 241 80-216 01/06 Fax: +49 241 80-22219 sek(a)i6.informatik.rwth-aachen.de www.hltpr.rwth-aachen.de

4 Jahre

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

informatik-vortraege