Welcome to the Wiki of the course '''Information Retrieval''' in the winter term 2015/2016

Here are the results for the official evaluation of this course.

The course is given by Prof. Dr. Hannah Bast and assisted by Elmar Haußmann (stand-in for the first three weeks: Björn Buchhold). It takes place every Tuesday from 4:15pm until 5:45pm in the seminar room SR 01-009/013 in building 101. The first lecture is on Tuesday, October 20, 2015 and the last lecture is on Tuesday, February 9, 2016. There will be no lecture on Tuesday, December 29, 2015 and Tuesday, January 5, 2016 (christmas break) and on [TODO: some other day which is yet to be selected]. That is 14 lectures altogether.

The tutors for this course are Björn Buchhold, Claudius Korzen, Sabine Storandt and Simon Weidner (weidnersimon@gmx.de). The administrator of the supporting systems (Daphne, SVN, Forum, Jenkins) is Axel Lehmann.

Important Links

• Here is the link to Daphne (our course management system, login with your RZ user name and password).

• Here is the link to the Forum (for announcements and questions, you are automatically a member when you have logged into Daphne).

• Code style profiles for Eclipse: Java, C++.

• Short introductions to SVN and Vim and the installation of gtest (for C++ only) can be found here (in German).

• The topics of this course will be similar (but not identical) to those of the courses Information Retrieval WS 2012/2013 and Information Retrieval WS 2013/2014.

• Here is information about the exams from previous years: WS 12/13, WS 13/14.

Lecture Slides, Video Recordings, Exercise Sheets, and Code

• Lecture 1, Tuesday, October 20, 2015 (Introduction, Inverted Index, Zipf's Law): Video Recording (Download), Slides, Exercise Sheet 1, Code from the lecture + TIP file, Dataset for ES1 (189,898 movies, title + description), Solutions for Sheet 1.

• Lecture 2, Tuesday, October 27, 2015 (Ranking, Evaluation): Video Recording (Download), Slides, Exercise Sheet 2, TIP file, Dataset for ES2 (movies2.txt ... like movies.txt, but without annoying ^M or \r characters), Benchmark for ES2 (query <tab> ground-truth as line numbers in movies2.txt), Table for your ranking results, Solutions for Sheet 2.

• Lecture 3, Tuesday, November 3, 2015 (Efficient List Intersection): Video Recording (Download), Slides, Exercise Sheet 3, Code from the lecture + posting lists, Table for performance results.

• Lecture 4, Tuesday, November 10, 2015 (Compression, Codes, Entropy): Video Recording (Download), Slides, Exercise Sheet 4, Solutions for Sheet 4.

• Lecture 5, Tuesday, November 17, 2015 (Fuzzy Search, Edit Distance, q-Gram Index): Video Recording (Download), Slides, Exercise Sheet 5, Code from the lecture, including TIPs for Exercises 1 - 3, Dataset for ES5, Table for your q-gram results, Solutions for Sheet 5.

• Lecture 6, Tuesday, November 24, 2015 (How to build a web application): Video Recording (Download), Slides, Exercise Sheet 6, Code snippets from lecture, Dataset for ES6 (description of columns), Table with your web apps, Solutions for Sheet 6.

• Lecture 7, Tuesday, December 1, 2015 (Web App Vulnerabilities, Cookies, Unicode): Video Recording (Download), Slides, Exercise Sheet 7, Code snippets from lecture, Dataset for ES7, Table with your web apps, Solutions for Sheet 7.

• Lecture 8, Tuesday, December 8, 2015 (Synonyms, Latent Semantic Indexing): Video Recording (Download), Slides, Exercise Sheet 8, Dataset for ES8 (same as for ES2), Code from the lecture and TIP file, Table with your results, Solutions for Sheet 8.

• Lecture 9, Tuesday, December 15, 2015 (Clustering, K-Means): Video Recording (Download), Slides, Exercise Sheet 9, Dataset for ES9 (same as for ES2), TIP file, Table with your results, Solutions for Sheet 9.

• Lecture 10, Tuesday, January 12, 2016 (Classification, Naive Bayes): Video Recording (Download), Slides, Exercise Sheet 10, Code for ES10, Datsets for ES10: movie genres (train), movie genres (test), movie ratings (train), movie ratings (test) , Solutions for Sheet 10.

• Lecture 11, Tuesday, January 19, 2016 (Linear Classifiers, Perceptrons, SVMs): Video Recording (Download), Slides, Exercise Sheet 11, Code for ES11, Datsets for ES11: Genres (Comedy vs. Thriller) train test, Ratings (R vs. not R) train test, Table with your results, Solutions for Sheet 11.

• Lecture 12, Tuesday, January 26, 2016 (Hypothesis Testing, Statistical Significance): Videoaufzeichnung (Download), Slides, Exercise Sheet 12, Code from the lecture, Datasets for ES12: Ratings (R vs. not R) train test (50) test (200) test (full), Table with your results, Solutions for Sheet 12.

• Lecture 13, Tuesday, February 2, 2016 (Knowledge Bases, SPARQL, Translation to SQL): Video Recording (Download), Slides, Exercise Sheet 13, Code and files from the lecture, Dataset for ES13 (10M facts from Freebase), Table with your results, Solutions for Sheet 13.

• Lecture 14, Tuesday, February 9, 2016 (Course Evaluation, Exam, Work at our Chair): http://ad-teaching.informatik.uni-freiburg.de/InformationRetrievalWS1516/lecture-14.avi, Slides, Evaluation results