Språkteknologi och textutvinning (Natural Language Processing and Text Mining) 7,5 hpUndervisningen bedrivs på engelska.
KursinnehållThis is an introductory course in Natural Language Processing (NLP) and Text Mining. The course covers basic and state-of-the-art techniques for the analysis and interpretation of natural language, focusing on methods involving machine learning on text, alternating theory with practice. The course includes assignments, in which the student implements algorithms for various NLP tasks and applications. After completing the course, the student shall have acquired a thorough theoretical understanding of, and practical experience with, modern algorithms for common NLP tasks and applications. Specifically, the student should understand and be able to apply all theoretical concepts covered.
The course includes the following elements:
- Regular Expressions and Text Normalization
- Data Annotation, Data Bias, Ethics and Fairness in NLP
- Word Embeddings and Word Senses
- Syntactic and Semantic Analysis
- Encoder-Decoder Models (Seq2Seq), Attention and Transformers
- State-of-the-art neural NLP models
- Analysis, Interpretation and Evaluation of NLP Models
- NLP Tasks, such as; Language Modelling , Text Classification and Clustering, Information Extraction, Named Entity Recognition, Semantic Role Labelling, Part-Of-Speech Tagging Coreference Resolution and Discourse Coherence
- NLP Applications, such as; Machine Translation, Information Retrieval, Text Generation, Summarization, Question Answering, Dialogue Systems, Chatbots, Automatic Speech Recognition (ASR) and Text-to-Speech Synthesis (TTS)
FörkunskapskravPassed courses at least 90 credits within the major subject Computer Engineering, Electrical Engineering (with relevant courses in Computer Engineering), or equivalent, or passed courses at least 150 credits from the programme Computer Science and Engineering, and completed courses Artificial Intelligence, 7,5 credits, Mathematics for Intelligent Systems, 7,5 credits, Machine Learning, 7,5 credits, Data Science Programming, 7,5 credits and Deep Learning, 7.5 credits or equivalent. Proof of English proficiency is required.
Utbildningsnivå: Avancerad nivå
Kursen ges vid: Tekniska Högskolan
Senast ändrad 2022-03-01 13:21:10