David Biesner

Mr. David Biesner

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 October 2021 in International Journal of Data Science and Analytics
Verified
Journal Article
Open access
PDF file
DBDavid Biesner
David Biesner
RRRajkumar Ramamurthy
Rajkumar Ramamurthy
RSRobin Stenzel
Robin Stenzel
MLMax Lübbering
Max Lübbering
LHLars Hillebrand
Lars Hillebrand
RSRafet Sifa
Rafet Sifa
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.

11 August 2022
Verified
Book Chapter
Closed access
PDF file
CCClayton Leroy Chapman
Clayton Leroy Chapman
LHLars Hillebrand
Lars Hillebrand
MSMarc Robin Stenzel
Marc Robin Stenzel
TDTobias Deußer
Tobias Deußer
DBDavid Biesner
David Biesner
RSRafet Sifa
Rafet Sifa

2 April 2024
Verified
Conference Paper
Open access
TGThore Gerlach
Thore Gerlach
SKStefan Knipp
Stefan Knipp
DBDavid Biesner
David Biesner
SEStelios Emmanouilidis
Stelios Emmanouilidis
KHKlaus Hauber
Klaus Hauber
NPNico Piatkowski
Nico Piatkowski

Verified
Journal Article
Open access
PDF file
LHLars Hillebrand
Lars Hillebrand
DBDavid Biesner
David Biesner
CBChristian Bauckhage
Christian Bauckhage
RSRafet Sifa
Rafet Sifa
Unsupervised topic extraction is a vital step in automatically extracting concise contentual information from large text corpora. Existing topic extraction methods lack the capability of linking relations between these topics which would further help text understanding. Therefore we propose utilizing the Decomposition into Directional Components (DEDICOM) algorithm which provides a uniquely interpretable matrix factorization for symmetric and asymmetric square matrices and tensors. We constrain DEDICOM to row-stochasticity and non-negativity in order to factorize pointwise mutual information matrices and tensors of text corpora. We identify latent topic clusters and their relations within the vocabulary and simultaneously learn interpretable word embeddings. Further, we introduce multiple methods based on alternating gradient descent to efficiently train constrained DEDICOM algorithms. We evaluate the qualitative topic modeling and word embedding performance of our proposed methods on several datasets, including a novel New York Times news dataset, and demonstrate how the DEDICOM algorithm provides deeper text analysis than competing matrix factorization approaches.

24 December 2023 in arXiv
Verified
Preprint
Open access
PDF file
TGThore Gerlach
Thore Gerlach
SKStefan Knipp
Stefan Knipp
DBDavid Biesner
David Biesner
SEStelios Emmanouilidis
Stelios Emmanouilidis
KHKlaus Hauber
Klaus Hauber
NPNico Piatkowski
Nico Piatkowski
Field-Programmable Gate Arrays (FPGAs) have asserted themselves as vital assets in contemporary computing by offering adaptable, reconfigurable hardware platforms. FPGA-based accelerators incubate opportunities for breakthroughs in areas, such as real-time data processing, machine learning or cryptography -- to mention just a few. The procedure of placement -- determining the optimal spatial arrangement of functional blocks on an FPGA to minimize communication delays and enhance performance -- is an NP-hard problem, notably requiring sophisticated algorithms for proficient solutions. Clearly, improving the placement leads to a decreased resource utilization during the implementation phase. Adiabatic quantum computing (AQC), with its capability to traverse expansive solution spaces, has potential for addressing such combinatorial problems. In this paper, we re-formulate the placement problem as a series of so called quadratic unconstrained binary optimization (QUBO) problems which are subsequently solved via AQC. Our novel formulation facilitates a straight-forward integration of design constraints. Moreover, the size of the sub-problems can be conveniently adapted to the available hardware capabilities. Beside the sole proposal of a novel method, we ask whether contemporary quantum hardware is resilient enough to find placements for real-world-sized FPGAs. A numerical evaluation on a D-Wave Advantage 5.4 quantum annealer suggests that the answer is in the affirmative.

28 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
DBDavid Biesner
David Biesner
TGThore Gerlach
Thore Gerlach
CBChristian Bauckhage
Christian Bauckhage
BKBernd Kliem
Bernd Kliem
RSRafet Sifa
Rafet Sifa
Many applications in automated auditing and the analysis and consistency check of financial documents can be formulated in part as the subset sum problem: Given a set of numbers and a target sum, find the subset of numbers that sums up to the target. The problem is NP-hard and classical solving algorithms are therefore not practical to use in many real applications. We tackle the problem as a QUBO (quadratic unconstrained binary optimization) problem and show how gradient descent on Hopfield Networks reliably finds solutions for both artificial and real data. We outline how this algorithm can be applied by adiabatic quantum computers (quantum annealers) and specialized hardware (field programmable gate arrays) for digital annealing and run experiments on quantum annealing hardware.