FI:IA161 NLP in practice - Course Information

IA161 Natural Language Processing in Practice

Extent and Intensity

1/1/0. 2 credit(s) (plus extra credits for completion). Type of Completion: k (colloquium).
In-person direct teaching

Teacher(s)

doc. RNDr. Aleš Horák, Ph.D. (lecturer)
RNDr. Zuzana Nevěřilová, Ph.D. (lecturer)
doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (lecturer)
RNDr. Marek Medveď, Ph.D. (lecturer)
Mgr. Radoslav Sabol (lecturer)
RNDr. Vít Suchomel, Ph.D. (lecturer)
Mgr. Tomáš Foltýnek, Ph.D. (lecturer)

Guaranteed by

doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics

Timetable

Wed 25. 9. to Wed 11. 12. Wed 10:00–11:50 A219

Prerequisites

All students should have basic practical knowledge of programming in Python. Overview knowledge of the natural language processing field at the level of introductory courses such as IB030 Introduction to Natural Language Processing or PA153 Natural Language Processing is expected. The seminar is given in English. Task solutions can be in English, Czech or Slovak.

Course Enrolment Limitations

The course is also offered to the students of the fields other than those the course is directly associated with.

fields of study / plans the course is directly associated with

there are 52 fields of study the course is directly associated with, display

Course objectives

The course participants will have the opportunity to learn about, test and experiment with advanced techniques of natural language processing (NLP) and to develop an understanding of the limits of those techniques. The course aims to introduce current research issues, and to meet in practice with particular programming techniques used in language technology applications.

Learning outcomes

After studying the course, the students will be able to:
- explain a selected NLP problem and list its main aspects;
- implement a basic or intermediate application for complex tasks in language processing, typically for Czech, Slovak, or English;
- create data resources (models, test sets) for a selected NLP problem and evaluate their assets;
- compare selected available tools for complex NLP tasks and apply them to chosen data resources with possible adaptations to particular purposes.

Syllabus

• The presented NLP problems will concentrate on practical problems connected with processing human-produced textual data. Particular topics include:
• Opinion mining, sentiment analysis
• Machine translation
• Parsing of Czech: Between Rules and Statistics
• Named Entity Recognition
• Building Language Resources from the Web (effective crawling, boilerplate removal, tokenisation, near duplicates identification)
• Language modelling
• Topic identification, topic modelling
• Extracting structured information from text
• Automatic relation extraction (hypernyms, synonyms, ...)
• Adaptive electronic dictionaries
• Terminology identification (keywords, key phrases)
• Anaphora resolution
• Stylometry
• Automatic language corrections

Literature

• Dan Jurafsky and James H. Martin. Speech and Language Processing (2020, 3rd ed. draft). https://web.stanford.edu/~jurafsky/slp3/
• J. Eisenstein, Introduction to Natural Language Processing (2019), MIT Press.
• https://www.aclweb.org/anthology/

Teaching methods

Each lecture consists of a one-hour lesson about the theoretical issues connected with a particular NLP problem, and a one-hour practical work in a computer laboratory devoted to the implementation, adaptation and evaluation of the presented techniques on real-world data.

Assessment methods

Solving tasks in the practical part of the lecture or in homeworks.

Language of instruction

English

Further Comments

Study Materials
The course is taught annually.

Teacher's information

http://nlp.fi.muni.cz/NlpInPracticeCourse

• Enrolment Statistics (recent)
  
• Permalink: https://is.muni.cz/course/fi/autumn2024/IA161