Natural Language Processing

Course Description

Lectures (M-II)

Fri 8:10 - 9:40

Labs (F1-248)

Fri 9:50 - 11:20

Lecture Slides

• 23th Feb: Course Info
• 2nd Mar: Text Pre-processing
• 9th Mar: Language Modeling
• 16th Mar: Dataset Splitting, Good-Turing, Spelling Correction, Noisy Channel
• 6th Apr: Naive Bayes, Sentiment Analysis
• 13th Apr: MaxEnt models, Named Entity Recognition
• 20th Apr: Relation Extraction, POS Tagging
• 27th Apr: Information Retrieval, Ranked IR
• 4th May: Word Meaning and Similarity, Question Answering
• 11th May: Deep NLP: Word Vectors, Text Classification
• 18th May: Introduction to Parsing, PCFGs and Constituency Parsing, Dependency Parsing

Programming Assignments

• 2nd Mar: Task 01: Minimum edit distance (deadline: 18th Mar)
• 9th Mar: Task 02: N-grams (deadline: 25th Mar)
• 16th Mar: Task 03: Spelling correction (deadline: 1st Apr)
• 6th Apr: Task 04: Sentiment Analysis (deadline: 26th Apr)
• 13th Apr: Task 05: Named Entity Recognition (deadline: 30th Apr)
• 11th May: Task 06: Word Embeddings and POS Tagging (deadline: 28th May)
• 18th May: Task 07: Dependency Parsing (deadline: end of terms period)

Project

Project Information

Learning Outcomes

The students will acquire knowledge and practical experience in the field of natural language processing. They will know how to effectively apply the underlying theory from probability, statistics, computational linguistics, and machine learning, to perform tasks involving unstructured text, such as spelling correction, text generation, sentiment analysis, information extraction, and question answering.

Class Syllabus

1. Text Processing
2. Language Modeling (n-grams), Spelling Correction
3. Text Classification (Naive Bayes), Sentiment Analysis
4. Named Entity Recognition (HMM, MaxEnt), Relation Extraction
5. POS Tagging, Parsing
6. Information Retrieval
7. Meaning Extraction, Question Answering

Lecturer

Ivor Uhliarik