PA154 Language Modeling
Faculty of InformaticsSpring 2025
- Extent and Intensity
- 2/0/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
In-person direct teaching - Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Zuzana Nevěřilová, Ph.D. (assistant) - Guaranteed by
- doc. Mgr. Pavel Rychlý, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - 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 32 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- English
- Further Comments
- The course is taught annually.
The course is taught: every week.
PA154 Language Modeling
Faculty of InformaticsSpring 2024
- Extent and Intensity
- 2/0/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Zuzana Nevěřilová, Ph.D. (assistant) - Guaranteed by
- doc. Mgr. Pavel Rychlý, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Tue 12:00–13:50 C416
- 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 51 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- English
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2023
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. Mgr. Pavel Rychlý, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Thu 16. 2. to Thu 11. 5. Thu 14:00–15:50 C511
- 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 51 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- English
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2022
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. Mgr. Pavel Rychlý, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Thu 17. 2. to Thu 12. 5. Thu 12:00–13:50 C416
- 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 51 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- English
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2021
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. Mgr. Pavel Rychlý, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Tue 10:00–11:50 Virtuální místnost
- 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 51 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2020
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. Mgr. Pavel Rychlý, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Mon 17. 2. to Fri 15. 5. Mon 12:00–13:50 A218
- 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 51 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2019
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Wed 10:00–11:50 C525
- 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 19 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2018
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Mon 14:00–15:50 B411
- 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 19 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.). - Learning outcomes
- At the end of the course students will be able to: use tools containing language models; understand the related theories and algorithms; include probabilistic models in the design of text processing applications; implement selected techniques in own applications.
- Syllabus
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2017
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Thu 14:00–15:50 C525
- 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 19 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.).
At the end of the course students will not only be able to use these tools, but mainly will understand the related theories and algorithms, which is often a key competence for the right (effective and correct) usage of these tools. - Syllabus
- NLTK toolkit
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2016
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Mon 10:00–11:50 C416
- 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 19 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.).
At the end of the course students will not only be able to use these tools, but mainly will understand the related theories and algorithms, which is often a key competence for the right (effective and correct) usage of these tools. - Syllabus
- NLTK toolkit
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Language Modeling
Faculty of InformaticsSpring 2015
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Wed 8:00–9:50 C416
- 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 18 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.).
At the end of the course students will not only be able to use these tools, but mainly will understand the related theories and algorithms, which is often a key competence for the right (effective and correct) usage of these tools. - Syllabus
- NLTK toolkit
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2014
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor) - Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Wed 10:00–11:50 G125
- 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 18 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.).
At the end of the course students will not only be able to use these tools, but mainly will understand the related theories and algorithms, which is often a key competence for the right (effective and correct) usage of these tools. - Syllabus
- NLTK toolkit
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2013
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Miloš Jakubíček, Ph.D. (seminar tutor)
RNDr. Vojtěch Kovář, Ph.D. (seminar tutor)
RNDr. Vít Suchomel, Ph.D. (assistant) - Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Tue 8:00–9:50 B411
- 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 25 fields of study the course is directly associated with, display
- Course objectives
- This course aims at providing the students with state-of-the-art in (mainly statistical) methods, algorithms and tools used for processing of large text corpora when they are created or subject to subsequent information retrieval.
These tools are practically used in many areas of natural language processing (semiautomatic building of text corpora, morphological analysis and desambiguation, syntactic analysis, effective indexation and search in text corpora, statistical machine translation, semantic analysis etc.).
At the end of the course students will not only be able to use these tools, but mainly will understand the related theories and algorithms, which is often a key competence for the right (effective and correct) usage of these tools. - Syllabus
- NLTK toolkit
- Elements of Probability and Information Theory
- Language Modeling in General and the Noisy Channel Model
- Smoothing and the Expectation-Maximization algorithm
- Markov models, Hidden Markov Models (HMMs)
- Viterbi Algorithm
- Tagging methods, HMM Tagging, Statistical Transformation Rule-Based Tagging
- Statistical Alignment and Machine Translation
- Text Categorization and Clustering
- Graphical Models
- Parallelization, MapReduce
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2012
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Thu 14:00–15:50 G124
- 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 25 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the principles of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2011
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Thu 10:00–11:50 C511
- 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 24 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the principles of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2010
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Tue 13:00–14:50 B313
- 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 24 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the principles of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Teaching methods
- lectures
- Assessment methods
- Written exam.
- Language of instruction
- Czech
- Further Comments
- The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2009
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Tue 15:00–16:50 B410
- 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 21 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the principles of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Assessment methods
- Lectures, written exam.
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2008
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Thu 8:00–9:50 B410
- 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 21 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the priciples of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2007
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Wed 18:00–19:50 B411
- 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 9 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the priciples of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2006
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Thu 10:00–11:50 B411
- 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 9 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the priciples of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Language of instruction
- Czech
- Further Comments
- Study Materials
The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2005
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. PhDr. Karel Pala, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D. - Timetable
- Tue 18:00–19:50 B411
- Course Enrolment Limitations
- The course is only offered to the students of the study fields the course is directly associated with.
- fields of study / plans the course is directly associated with
- there are 9 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the priciples of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Language of instruction
- Czech
- Further Comments
- The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2004
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- prof. PhDr. Karel Pala, CSc. (lecturer)
- Guaranteed by
- prof. PhDr. Karel Pala, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: prof. PhDr. Karel Pala, CSc. - Timetable
- Tue 18:00–19:50 B204
- Course Enrolment Limitations
- The course is only offered to the students of the study fields the course is directly associated with.
- fields of study / plans the course is directly associated with
- there are 8 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the priciples of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Language of instruction
- Czech
- Further Comments
- The course is taught annually.
PA154 Corpus Tools
Faculty of InformaticsSpring 2003
- Extent and Intensity
- 2/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- prof. PhDr. Karel Pala, CSc. (lecturer)
- Guaranteed by
- prof. PhDr. Karel Pala, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: prof. PhDr. Karel Pala, CSc. - Timetable
- Tue 10:00–11:50 B204
- Course Enrolment Limitations
- The course is only offered to the students of the study fields the course is directly associated with.
- fields of study / plans the course is directly associated with
- there are 8 fields of study the course is directly associated with, display
- Course objectives
- The subject is an introduction to the corpus linguistics a computer lexicography. It offers the basics of the corpora types, corpus tools, tagging and disambiguation. In the part dealing with the computer lexicography one can find the explanation about the machine readable dictionaries and lexical databases and the priciples of their building.
- Syllabus
- Text corpora and their types. Standardization of the corpus data - SGML, XML, TEI. Building corpora. Corpus managers and processors (CQP, Manatee), graphical interface (GCQP, Bonito), concordance programs (OCP). Tagging and taggers (ajka for Czech). Morphological, syntactic and semantic tagging (WSD). Disambiguation and disambiguators (rule based - DIS, stochastic and others). Parallel corpora, alignment and aligners. Using corpora in computer lexicography, context, word sense disambiguation. Machine readable dictionaries and their types. Tools for electronic dictionaries - browsers and editors. Lexicographer's workbench. Lexical databases WordNet and EuroWordNet and tools for handling them: Polaris, Persicope, VisDic.
- Literature
- Language of instruction
- Czech
- Further Comments
- The course is taught annually.
- Enrolment Statistics (recent)