+**********************************************************************
*
*
* Einladung
*
*
*
* Informatik-Oberseminar
*
*
*
+**********************************************************************
Zeit: Freitag, 12. Juli 2019, 10.00 Uhr
Ort: Informatikzentrum, E3, Raum 9222
Referent: Dipl.-Inform. Malte Nuhn
Thema: Unsupervised Training with Applications in Natural Language
Processing//
Abstract:
The state-of-the-art algorithms for various natural language processing
tasks require large amounts of labeled training data. At the same time,
obtaining labeled data of high quality is often the most costly step in
setting up natural language processing systems.Opposed to this,
unlabeled data is much cheaper to obtain and available in larger
amounts.Currently, only few training algorithms make use of unlabeled
data. In practice, training with only unlabeled data is not performed at
all. In this thesis, we study how unlabeled data can be used to train a
variety of models used in natural language processing. In particular, we
study models applicable to solving substitution ciphers, spelling
correction, and machine translation. This thesis lays the groundwork for
unsupervised training by presenting and analyzing the corresponding
models and unsupervised training problems in a consistent manner.We show
that the unsupervised training problem that occurs when breaking
one-to-one substitution ciphers is equivalent to the quadratic
assignment problem (QAP) if a bigram language model is incorporated and
therefore NP-hard. Based on this analysis, we present an effective
algorithm for unsupervised training for deterministic substitutions. In
the case of English one-to-one substitution ciphers, we show that our
novel algorithm achieves results close to human performance, as
presented in [Shannon 49].
Also, with this algorithm, we present, to the best of our knowledge, the
first automatic decipherment of the second part of the Beale
ciphers.Further, for the task of spelling correction, we work out the
details of the EM algorithm [Dempster & Laird + 77] and experimentally
show that the error rates achieved using purely unsupervised training
reach those of supervised training.For handling large vocabularies, we
introduce a novel model initialization as well as multiple training
procedures that significantly speed up training without hurting the
performance of the resulting models significantly.By incorporating an
alignment model, we further extend this model such that it can be
applied to the task of machine translation. We show that the true
lexical and alignment model parameters can be learned without any
labeled data: We experimentally show that the corresponding likelihood
function attains its maximum for the true model parameters if a
sufficient amount of unlabeled data is available. Further, for the
problem of spelling correction with symbol substitutions and local
swaps, we also show experimentally that the performance achieved with
purely unsupervised EM training reaches that of supervised training.
Finally, using the methods developed in this thesis, we present results
on an unsupervised training task for machine translation with a ten
times larger vocabulary than that of tasks investigated in previous work.
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
+**********************************************************************
*
*
* Einladung
*
*
*
* Informatik-Oberseminar
*
*
*
+**********************************************************************
Zeit: Donnerstag, 12. September 2019, 10.00 Uhr
Ort: AH VI (2356|051), Ahornstr. 55
Referent: Simon Hacks, M.Sc.
Lehr- und Forschungsgebiet Informatik 3
Thema: Improving the Quality of Enterprise Architecture Models: Processes
and Techniques
Abstract:
Information technology (IT) pervades organizations more and more and becomes
increasingly important for their business models. It has evolved from a
purely supportive role to an important strategic pillar in many
organizations. Even more, it is important that IT is aligned to the needs of
the organization. Approaches that realize this are often subsumed under the
term "business-IT-alignment". One instrument for achieving
business-IT-alignment is Enterprise Architecture (EA). EAs provide a
holistic perspective on the structure of the organization and provide a set
of techniques to guide and steer the evolution of the organization to a
desired goal state.
A key artifact of EA is the EA model. It abstracts the elements and their
relationships to an understandable and manageable measure. Usually
enterprise architects model business processes, applications, hardware
components, data models and customer relationships. Based on the information
stored in the EA model, the organization's management makes important
decisions regarding future focus. Contrary, also on the operational level,
the model can provide important information, for example which application
is used in which business environment and exchanges data with other
applications.
In order to be able to derive meaningful decisions from the EA model, their
quality is of crucial importance. Therefore, this work is elaborates on
developing different processes and techniques that ensure the quality of the
EA model.
First, we present a process to ensure the quality of the EA model, where
model maintenance is understood as a continuous evolution. For this purpose,
we define different steps, which have to be considered in such a process.
This process will serve as foundation for a continuous delivery pipeline
that will help automate as many of these steps as possible. Next, we present
an approach that allows storing contrary information in EA models.
In addition to the aforementioned processes, we developed also several
techniques to improve the quality of EA models. However, for improvement, we
need a method to evaluate the quality, which we also introduce within this
work. Subsequently, we facilitate machine-learning techniques to support the
modeler reuse existing elements of the model. In addition, we compare the
performance of different algorithms to determine the best on in a certain
situation. Additionally, we present a method to identify unnecessary
elements in the model.
Es laden ein: die Dozentinnen und Dozenten der Informatik