BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:4792-409@gi.de
CLASS: PUBLIC
SUMMARY:Natural Language Processing in Python (English)
DESCRIPTION:Trainer: Dr. Matthias Aßenmacher\n\nCourse duration: 4 days, ea
 ch from 09:00 - 13:30 CET (Online-Live-Seminar)\n\nCourse language: English
  (we can switch to German if all participants are fluent in German)\n\nIn t
 he last five to six years, researchers have achieved some breakthrough deve
 lopments in text mining and natural language processing (NLP). These breakt
 hroughs are largely based on three influential factors:\n\n- Conceptually n
 ew frameworks from the field of Deep Learning.\n\n- Significant improvement
 s in computational resources,\n\n- (Significantly) Larger amounts of availa
 ble data (Big Data).\n\nIn this course, we will start with the basics of te
 xt processing in Python and learn about classical feature engineering appro
 aches from the field of Machine Learning. We will then have a detailed look
  at the methodology that can be seen as the beginning of a new era in NLP: 
 the so-called Word Embeddings or Word Vectors. We will further discuss the 
 integration of these word embeddings into modern Deep Learning architecture
 s, in particular deep recurrent neural networks (RNNs). Since the so-called
  "attention" mechanism and transfer learning form the basis of the most cur
 rent state-of-the-art models such as BERT & Co., we will cover these two to
 pics in detail in the final part of the course.\n\nOverall, the course will
  cover the following topics:\n\nPart 1: We will first illustrate the import
 ance of NLP with some examples. After that, there will be an introduction t
 o dealing with text data and their potential representations in Machine Lea
 rning. Afterward, so-called Fully-Connected-Neural-Networks (FCNNs) will be
  introduced as an important basis for the rest of the course.\n\nPart 2: We
  will deal exclusively with so-called neural representations of texts. We w
 ill start with the idea of language modeling using the Neural probabilistic
  language model (Bengio et al, 2003). Then, the Word2Vec framework (Mikolov
  et al., 2013), the Doc2Vec framework (Mikolov and Le, 2014), and the FastT
 ext framework (Bojanowski et al, 2017) are introduced. Each of these framew
 orks will be accompanied by hands-on sessions for practical implementation 
 of what has been learned.\n\nPart 3: We will focus on Deep Learning and cur
 rent state-of-the-art architectures. We will take an in-depth look at exist
 ing transfer learning resources and apply what we have learned in a final h
 ands-on session.\n\nHands-On Sessions: For the hands-on parts of the course
 , practice exercises will be provided in the form of Jupyter notebooks that
  participants can use to complete the exercises themselves.\n\nPrerequisite
 s: Basic knowledge of Python and Supervised Machine Learning methods
LOCATION:Zoom (Online)
DTSTAMP:20220311T083852Z
DTSTART:20221004T070000Z
DTEND:20221007T113000Z
END:VEVENT
END:VCALENDAR