TH Köln

Master Digital Sciences

Dokumente zur Akkreditierung des Studiengangs

Modul »Natural Language Processing« (NLP)

Informationen zur Organisation des Moduls

Modulverantwortung
Prof. Dr. Philipp Schaer (Fakultät F03)
Lehrende
Prof. Dr. Philipp Schaer (Fakultät F03), Prof. Dr. Klaus Lepsky (Fakultät F03)
Sprache
Englisch
Angeboten im
Sommersemester (Dauer 1 Semester)
Ort
Remote
Anzahl Teilnehmer*innen
minimal 1, maximal 20
Vorbedingung
Not allowed for students coming from the DIS, B.Sc.
Empfehlung
Basic knowledge of Python.
ECTS
3
Aufwand
Gesamtaufwand 90h
Kontaktzeit
30h (20h Vorlesung / 10h Übung)
Selbstlernzeit
60h
Prüfung
Fachgespräch oder Klausur
Vermittelte Kompetenzen
Analyze Domains, Model Systems, Implement Concepts
Beziehung zu globalen Studiengangskriterien
Interdisziplinarität, Digitalisierung

Beitrag zu Handlungsfeldern

Nachfolgend ist die Zuordnung des Moduls zu den Handlungsfeldern des Studiengangs aufgeführt, und zwar als anteiliger Beitrag (als ECTS und inhaltlich). Dies gibt auch Auskunft über die Verwendbarkeit des Moduls in anderen Studiengängen und über die Beziehung zu anderen Modulen im selben Studiengang.

Handlungsfeld ECTS (anteilig) Modulbeitrag zum Handlungsfeld
Generating and Accessing Knowledge 2

Natural Language Processing (NLP) deals with techniques that enable computers to understand the meaning of text, which is written in a natural language.

Acting Responsibly 1

The module also deals with the impacts of this technique.

Learning Outcome

Natural Language Processing (NLP) deals with techniques that enable computers to understand the meaning of text, which is written in a natural language. Thus NLP constitutes an essential part for modern text-based challenges. As a science NLP can be considered as the field, where Computer Science, Artificial Intelligence, Machine Learning and Linguistics overlap.

(WHAT?)

In this course the students will learn about basis techniques and theories of NLP. However, the lecture does not only provide the theory but also the implementation of relevant and state-of-the-art NLP procedures. Topics of this course are well-established approaches like tool-based language processing, dictionary, or lexical approaches.

(HOW?)

By applying state-of-the-art techniques on real-world data sets students learn to extract knowledge from natural language corpora. These allow them to analyze, discover and evaluate phenomena hidden in texts.

(WHY?)

NLP enables applications like intelligent search engines, dialog systems, question-answering systems, machine translation, document classification, sentiment analysis or opinion mining. However, the lecture does not only provide the theory but also the implementation of the relevant NLP procedures. This allows them to conduct own applied research on given or self-crawled data from a variaty of data sources, like commercial or research-related scenarios.

Inhaltliche Beschreibung des Moduls

  1. Introduction, show case indexing: thesauri vs. statistical approaches - show, compare and discuss
  2. Access text and preprocess (assessing text files, web sites, corpora, segmentation into words and sentences, regex)
  3. Morphology (normalisation, stemming, lemmatisation, POS-Tagging …)
  4. Lexical processing (WordNet, DBPedia)
  5. Basic language modelling
  6. Information extraction
  7. Sentiment analysis

Lehr- und Lernformen

The course follows a hybrid format, where lecture videos are provided online and classroom time is used for discussion, exercises, and working on assignments.

  • This course involves self-study (which can be completed online): You’re expected to watch the lecture videos, read the corresponding book chapters/sections listed on the last slide of each lecture deck, as well as complete the exercises on GitHub.
  • There is also a classroom component which is not obligatory, but highly recommended for an optimal learning experience. This involves discussion and exercises in a regular or virtual classroom setting.

Zur Verfügung gestelltes Lehrmaterial

  • slides and recorded lectures
  • excersises
  • access to standard NLP text corpora

Weiterführende Literatur

  • Speech and language processing : an introduction to natural language processing, computational linguistics, and speech recognition (2009) by Dan Jurafsky
  • Foundations of statistical natural language processing (18 June 1999) by Christopher D. Manning, Hinrich Schuetze
  • Natural Language Processing with Python (2009) by Steven Bird, Ewan Klein, Edward Loper
  • Neural Network Methods in Natural Language Processing (Morgan and Claypool Publishers, 2017) by Yoav Goldberg
  • Natural Language Processing with PyTorch (O’ Reilly 2019) by D. Rao, B. MacMahan
  • Natural Language Processing in Action (Manning 2019) by H. Lane, H. Hapke, C. Howard