EventoWeb
Zürcher Hochschule für Angewandte Wissenschaften
Menu Home User Menu
Not registered Login
[ German (Switzerland) German (Switzerland) ]   [ English ]
[ de de ]   [ en ]
Not registered Login
t.BA.DS.NLP.20HS (Introduction to Natural Language Processing) 
Module: Introduction to Natural Language Processing
This information was generated on: 06 December 2024
No.
t.BA.DS.NLP.20HS
Title
Introduction to Natural Language Processing
Organised by
T CAI
Credits
4

Description

Version: 2.0 start 01 February 2023
 

Short description

 This module introduces the basic methods and technologies of Natural Language Processing (NLP). Typical tasks and solution approaches are presented and implemented based on practice-oriented projects.

Module coordinator

 Cieliebak Mark (ciel)

Learning objectives (competencies)
Objectives Competences Taxonomy levels
The students know typical tasks in the field of NLP. F K1
Students can integrate existing technical solutions for a problem into their problem solving.  F, M K3
Students can plan and document machine-based experiments on textual data in a structured way. M K3
The students can document their results in the form of a scientific report.  M K3
The students work together actively and goal-oriented in a team and take responsibility for the development of the common project. M, SO, SE K3
Students can realize a larger and complex NLP project from vision to solution. F, M K5

Module contents

 Methods and technologies in the field of NLP are taught by means of three practice-oriented tasks covering typical topics such as clustering, text classification, and text generation (e.g., abstractive summarization).

For each task, the relevant solution approaches are presented. These include, but are not limited to, the following topics:

- Preprocessing of the data: Tokenization, stemming, etc.
- Representation of the data: Vector-Space Models, TF-IDF, Pretrained Language Models/Embeddings etc.
- Machine Learning Models and Algorithms: SVM, Neural Networks, etc.
- Evaluation methods: Precision/Recall, F-Score, ROUGE etc.
- Established tools and frameworks: e.g. nltk, Pytorch, huggingface etc.
- Experimental setup and documentation of results

For each task, students will develop a solution individually or in small groups of up to 3 people. The documentation of the solution will be assessed afterwards.
 
 

Teaching materials

 The necessary material is provided during in class.
 

Supplementary literature

 -

Prerequisites

 -

Teaching language

 (X) German ( ) English

Part of International Profile

 ( ) Yes (X) No

Module structure

 Type 2a
  For more details please click on this link: T_CL_Modulauspraegungen_SM2025

Exams
Description Type Form Scope Grade Weighting
Graded assignments during teaching semester Short Report or Poster written ca. 1 page Grade 20%
Graded assignments during teaching semester Short Report written ca. 2-4 page Grade 20%
End-of-semester exam Scientific Paper written ca 4-8 pages Grade 60%

Remarks

 Individual performance can also have an influence on individual grades in group work, i.e. not all group members must always receive the same grade.
 

Legal basis

 The module description is part of the legal basis in addition to the general academic regulations. It is binding. During the first week of the semester a written and communicated supplement can specify the module description in more detail.

Note

Course: Einführung in Natural Language Processing - Vorlesung
No.
t.BA.DS.NLP.20HS.V
Title
Einführung in Natural Language Processing - Vorlesung

Note

  • No module description is available in the system for the cut-off date of 02 August 2099.