Concept

Text corpus

Related lectures (31)

Latent Semantic Indexing: Concepts and Applications

Explores latent semantic indexing, vocabulary construction, document matrix creation, query transformation, and document retrieval using cosine similarity.

Neural Networks for NLP

Covers modern Neural Network approaches to NLP, focusing on word embeddings, Neural Networks for NLP tasks, and future Transfer Learning techniques.

Text Processing: Humanities Computing and Linguistics

Explores the processing of large digital texts, revealing hidden patterns and structures, and the convergence of Humanities Computing and Computational Linguistics.

Introduction to NLP and the Course

Covers the basics of Natural Language Processing, including challenges, linguistic processing levels, and the impact of power laws.

Word Embeddings: Introduction and Applications

Introduces word embeddings, explaining how they capture word meanings based on context and their applications in natural language processing tasks.

Text Data Processing: Basics & Techniques

Introduces the basics of text data processing, covering document retrieval, classification, sentiment analysis, and topic detection.

Taxonomy Induction: Relations Extraction and Graph Construction

Covers relations extraction and graph construction in taxonomy induction, emphasizing noise reduction for accurate graphs.

Handling Text: Document Retrieval, Classification, Sentiment Analysis

Explores document retrieval, classification, sentiment analysis, TF-IDF matrices, nearest-neighbor methods, matrix factorization, regularization, LDA, contextualized word vectors, and BERT.

Text Retrieval: Document Ranking

Covers text retrieval tasks with document ranking and re-ranking, using a large corpus for evaluation.

Information Retrieval: Fagin's Algorithm

Covers the implementation of Fagin's algorithm for information retrieval, focusing on efficient document retrieval.

Indexing for Information Retrieval

Explores indexing techniques, inverted files, map-reduce models, and trie usage for efficient information retrieval.

Keyphrase Extraction

Covers keyphrase extraction, a method to extract important phrases from text for document summarization, indexing, and search.

Text Processing: Large Digital Text Collections Analysis

Delves into the processing of large digital text collections, exploring hidden regularities, text reuse, and TF-IDF analysis.

NLP Pre-processing: Tokenization, Stop Words, Lemmatization

Covers tokenization, stop words removal, and lemmatization for NLP tasks.

Information retrieval: vector space

Covers the basics of information retrieval using vector space models and practical exercises on relevance feedback and posting list scanning.

Probabilistic Retrieval

Covers Probabilistic Information Retrieval, modeling relevance as a probability, query expansion, and automatic thesaurus generation.

Information Extraction: Approaches and Techniques

Covers Information Extraction approaches, including hand-written patterns and supervised learning.

Natural Language Processing: Understanding Transformers and Tokenization

Provides an overview of Natural Language Processing, focusing on transformers, tokenization, and self-attention mechanisms for effective language analysis and synthesis.

Text Understanding

Explores Text Understanding, focusing on Named Entities, Information Extraction, and Machine Reading methods.

Text Encoding: Unicode and XML

Explores text encoding evolution, Unicode, XML, OCR, HTR, and handling spelling variations in historical texts.