informatik-vortraege Juli 2018

informatik-vortraege@lists.rwth-aachen.de

2 Teilnehmer
2 Diskussionen

Ankündigung Oberseminar Herr Erion Elmasllari am 06.08.2018 um 14 Uhr

von Daniele Gloeckner

************************************************************************ ** * Einladung * * * Informatik-Oberseminar * * ************************************************************************ Zeit: Montag, 06.08.2018, 14.00 Uhr Ort:: Seminarraum 5053.2 (B-IT Research School, ggü. AH 6) Referent: Herr Erion Elmasllari, M.Sc. Titel: A Framework for the Successful Design and Deployment of Electronic Triage Systems Abstract: Triage -- the prioritisation of victims by emergency of treatment -- suffers from various well-known problems that impact victims' survival chances. Many electronic triage systems have been proposed as a solution, but none of them have been accepted by emergency responders. Furthermore, the reasons for the rejection have never been satisfyingly analyzed until now. The dissertation identifies key criteria for the acceptance of electronic triage systems and presents a conceptual framework, targeted at system designers, to actively guide them towards well-accepted e-triage implementations. An example implementation based on the framework is designed, implemented, and evaluated in large-scale trials, followed by a retrospective, higher-level look on the limits, risks, and intrinsic issues of introducing ICT support in triage. Es laden ein: Die Dozenten der Informatik

5 Jahre, 9 Monate

Ankuendigung Oberseminar am 01.08.18 um 10:00 Uhr

von Sekretariat I6

************************************************************************ * * Einladung * * * * Informatik-Oberseminar * ************************************************************************ Zeit: Wednesday, August 1st 2018, 10:00am Ort: Informatik E3, Room 9222 Referent: Dipl.-Inform. Matthias Huck Titel: Statistical Models for Hierarchical Phrase-based Machine Translation Abstract: Machine translation systems automatically translate texts from one natural language to another. The dominant approach to machine translation has been phrase-based statistical machine translation for many years. In statistical machine translation, probabilistic models are learned from training data, and a decoder is conducting a search to determine the best translation of an input sentence based on model scores. Phrase-based systems rely on elementary translation units that are continuous bilingual sequences of words, called phrases. The hierarchical approach to statistical machine translation allows for phrases with gaps. Formally, the hierarchical phrase inventory can be represented as a synchronous context-free grammar that is induced from bilingual text, and hierarchical decoding can be carried out with a parsing-based procedure. The hierarchical phrase-based machine translation paradigm enables modeling of reorderings and long-distance dependencies in a consistent way. The typical statistical models that guide hierarchical search are fairly similar to those employed in conventional phrase-based translation. In this work, novel extensions with statistical models for hierarchical phrase-based machine translation are developed, with a focus on methods that do not require any syntactic annotation of the data. Specifically, enhancements of hierarchical systems with extended lexicon models that take global source sentence context into account are investigated; various lexical smoothing variants are examined; reordering extensions and a phrase orientation model for hierarchical translation are introduced; word insertion and deletion models are presented; techniques for training of hierarchical translation systems with additional synthetic data are suggested; and a training method is proposed that utilizes additional synthetic data which is created via a pivot language. The beneficial impact of the extensions on translation quality is verified by means of empirical evaluation on various language pairs, including Arabic-English, Chinese-English, French-German, English-French, and German-French. Es laden ein: Die 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

5 Jahre, 9 Monate

2024

2023

2022

2021

2020

2019

2018

informatik-vortraege Juli 2018