194.093 Natural Language Processing and Information Extraction
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2021W, VU, 2.0h, 3.0EC
TUWEL

Course evaluation

Properties

  • Semester hours: 2.0
  • Credits: 3.0
  • Type: VU Lecture and Exercise
  • Format: Distance Learning

Learning outcomes

After successful completion of the course, students are able to extract structure from natural language data by applying standard methods for text segmentation, word and sequence tagging, or syntactic parsing. They will have a high-level overview of the most important rule-based and learning-based approaches to each task and the standard methods for evaluating them. Students will gain a fundamental understanding of artificial neural networks and methods for training them, with a special emphasis on architectures for processing sequential data, allowing them to solve a variety of NLP tasks with deep learning. An overview of information extraction tasks will be given, allowing students to approach various problems involving the extraction of structured information from unstructured text data. A survey of common specialized IE tasks is also provided, acquainting the students with some of the most common NLP applications.

Subject of course

- Basics of text processing: segmentation, tokenization, decompounding, stemming, lemmatization; regular expressions

- N-gram language modeling, simple classification tasks in NLP

- Part-of-speech tagging, named entity recognition, and shallow parsing with Hidden Markov Models

- Syntactic representations and syntactic parsing

- Basics of natural language semantics

- Neural network basics. Feed forward networks and recurrent neural networks

- Sequence modeling and sequence-to-sequence models. 

- Neural language modeling. Word vectors and contextualized language models. 

- Information extraction tasks: entity recognition, relation extraction, knowledge base population

- Information extraction applications: summarization, question answering, chatbots

Teaching methods

Lectures on the fundamentals

1 Term project (done in groups) with Milestones

Mode of examination

Immanent

Additional information

The link to the online lectures is in TUWEL.


Workload for Students (in hours):

  • Lectures: 24
  • Milestone 1: 8
  • Milestone 2: 8
  • Final Project: 35

Summe: 75

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Fri13:00 - 15:0008.10.2021 - 21.01.2022 Natural Language Processing and Information Extraction Lecture
Natural Language Processing and Information Extraction - Single appointments
DayDateTimeLocationDescription
Fri08.10.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri15.10.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri22.10.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri29.10.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri05.11.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri12.11.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri19.11.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri26.11.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri03.12.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri10.12.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri17.12.202113:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri14.01.202213:00 - 15:00 Natural Language Processing and Information Extraction Lecture
Fri21.01.202213:00 - 15:00 Natural Language Processing and Information Extraction Lecture

Examination modalities

15% for Milestone 1 15% for Milestone 2 50% for the final solution 10% for the presentation 10% for the management summary

Course registration

Begin End Deregistration end
20.09.2021 08:00 03.11.2021 23:55 03.11.2021 23:55

Curricula

Study CodeSemesterPrecon.Info
066 645 Data Science

Literature

No lecture notes are available.

Language

English