|
Information Retrieval and Text Mining
- Dozent/in
- Prof. Dr. Roman Klinger
- Angaben
- Vorlesung und Übung
Rein Präsenz 4 SWS, benoteter Schein, Unterrichtssprache Deutsch
Zeit und Ort: Di 18:00 - 20:00, WE5/04.014; Do 8:00 - 10:00, WE5/04.014; Bemerkung zu Zeit und Ort: The first meeting will be in the first week of the teaching period
- Voraussetzungen / Organisatorisches
- Prior knowledge:
programming in some object-oriented programming language of your choice
Typical work load:
• Meetings and talks: 22 lectures, 5 exercise sessions; ~42h
(plus preparation and reviewing the material)
• Programming and Pen & Paper exercises:
5 assignments with each ~2 weeks of time; ~8–16 hours estimated work time in a team, depending on prior knowledge
Language: English/German
(course language as students prefer, submissions as individually preferred)
- Inhalt
- Want to learn how to build an Internet search engine from scratch? Want to learn the fundaments for natural language processing and textual document processing?
In this class, offered as a lecture in a lecture hall with all lectures being recorded and made available as videos, we discuss fundamental data structures for information retrieval, ranking, classification, or clustering of documents.
This class also creates the fundament for further natural language processing methods, including natural language understanding and deep learning for natural language processing. I plan to offer the following lectures in the future.
Participation in the lectures is not mandatory, but if you like to interact, ask questions and actively discussed, very appreciated. Active participation in the exercises is expected, but participation is also not mandatory.
In more detail, the following topics will be part of this class:
• Boolean Retrieval, Term Vocabularies and Postings Lists, Dictionaries and Tolerant Retrieval, Spelling Correction, Index Construction, Compression, Scoring, Ranking, Evaluation, Query Expansion, Probabilistic IR
• Text Classification, Naïve Bayes, MaxEnt Classifier, kNN, Neural Networks, Feature Selection, Vector space classification, Document similarities
• Learning to Rank, Learning to Score
• Flat clustering, Hierarchical Clustering, Evaluation
- Empfohlene Literatur
- General literature: We mostly follow the material available at www.informationretrieval.org with some additional lectures and updates to more recent work.
- Englischsprachige Informationen:
- Title:
- Information Retrieval and Text Mining
- Credits: 6
- Institution: Lehrstuhl für Grundlagen der Sprachverarbeitung
Hinweis für Web-Redakteure: Wenn Sie auf Ihren Webseiten einen Link zu dieser Lehrveranstaltung setzen möchten, verwenden Sie bitte einen der folgenden Links:Link zur eigenständigen Verwendung Link zur Verwendung in Typo3
|
|
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|