👷 Introduction to Information Retrieval

Index compression, and scoring, term weighting and the vector space model 8. 3. 2022

Lecture

Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/lectures/2022-p05comp.pdf
Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/lectures/2022-p06score.pdf

Index compression, and scoring, term weighting and the vector space model
Lecture from week 4

Readings

Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/readings/05comp.pdf
Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/readings/06vect.pdf
Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/readings/lecture6-tfidf-1per.pdf
Soft Cosine Similarity
A tutorial for computing the soft cosine similarity measure between two documents in Python.

Seminar

Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/seminars/week-04-index-compression-and-scoring-term-weighting-and-the-vector-space-model-solution.pdf
Index compression
Google Colaboratory code for seminars in the fourth week
Scoring, term weighting, and the vector space model
Google Colaboratory code for seminars in the fourth week

Tolerant retrieval, and index compression, and scoring
Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/whiteboards/
Scoring, term weighting and the vector space model
Seminar 03 from week 4
Chyba: Odkazovaný objekt neexistuje nebo nemáte právo jej číst.
https://is.muni.cz/el/fi/jaro2022/PV211/um/whiteboards/spring_2021/seminar01/week04/Notes_for_week_4.pdf

First term project

Below, can find the homework vaults for submitting the first term project.

First term project assignment
Google Colaboratory code for the first term project

First term project leaderboard
Google Spreadsheet leaderboard for the first term project
First term project JupyterHub (beta)
A JupyterHub cluster kindly provided to the course by ICT MU. You can use JupyterHub to work on your first term project assignment. Compared to Google Colaboratory, JupyterHub offers up to 32 CPUs, 2 NVIDIA A40 GPUs and 64G RAM. Notebooks will be closed after 3 days of inactivity; make sure you download your work!
Gensim: Topic Modeling for Humans
Core Tutorials: New Users Start Here!

First term project (seminar group 01)
Homework vault for the first term project (a ranked unsupervised retrieval system for Cranfield collection).
First term project (seminar group 02)
Homework vault for the first term project (a ranked unsupervised retrieval system for Cranfield collection).
First term project (seminar group 03)
Homework vault for the first term project (a ranked unsupervised retrieval system for Cranfield collection).
Předchozí
Následující