Schedule and course plan TO BE UPDATED!

Period 3 THIS IS LAST YEAR'S SCHEDULE Where and When Activity Reading Examination January 2013.15-15.00B2 Lecture 1: Introduction, boolean retrieval, course practicalities Hedvig Kjellström Manning Chapter 1 January 2310.15-12.00D3 Lecture 2: Term vocabulary, dictionaries and tolerant retrievalJohan Boye Manning Chapter 2, 3 January 2713.15-15.00Q2 Lecture 3: Evaluation of search enginesJussi Karlgren Manning Chapter 8 February 1013.00-19.00spelhallen Computer hall session Oral examination of Assignment 1 in front of computer February 1310.15-12.00Q2 Lecture 4: Scoring, weighting, vector space modelHedvig Kjellström Manning Chapter 6, 7 February 1713.15-15.00Q2 Lecture 5: Retrieval of documents with hyperlinksHedvig Kjellström Manning Chapter 21, Avrachenkov Sections 1-2 February 2413.15-15.00Q2 Lecture 6: IR Beyond one shot

Jussi Karlgren

Manning Chapter 9, Robertson March 315.00-18.00Orange Computer hall session Oral examination of Assignment 2 in front of computer March 610.15-12.00B3 Lecture 7: Some useful additions to a search engine, Random IndexingViggo Kann Sahlgren March 2413.15-15.00D3 Lecture 8: Probabilistic information retrieval, language modelsHedvig Kjellström

Manning Chapter 11, 12 Period 4 THIS IS LAST YEAR'S SCHEDULE Where and When Activity Reading Examination March 3113.00-16.00Röd Computer hall session Oral examination of Assignment 3 in front of computer April 1413.15-15.00D3 Lecture 9: Guest lectures

Boxun Zhang, Spotify

Algorithmic Music Discovery at Spotify

Today, Spotify has over 60 million active users and over 30 millionsongs. One key mission of Spotify is to help users discover goodmusic, which is achieved by serving users good recommendations.In this talk, I will introduce briefly the recommender system behindthe Discover feature in Spotify, and some challenges we have.

Simon Stenström, Findwise

Search From the Trenches

What distinguished a search engine from a search solution? This talk focuses on the part of findability that a search engine just doesn't do well on its own. How can we solve that? What else do you need?

April 2813.15-15.00D3 Lecture 10: Guest lectures

Roelof Pieters, KTH and Graph Technologies R&D AB

Deep Learning for Information Retrieval

From 2013 to 2020, the digital universe will grow by a factor of 10. Not only the size of data is changing, but also its shape: from mainly text-based to increasingly visual, and audio. Search engines are having a hard time to keep up. Deep Learning, a new branch of machine learning, is one way to deal with this enormous growth of information. In this talk I will give a brief introduction to deep learning, and explain how it can help in making content searchable through 2 specific deep-learning based approaches: multi-modal methods, which can learn a single united visual-semantic representation of text and images, as well as deep graph-based methods and textual embeddings, which can learn latent features of text, and can find disentangle and find structure in the chaos and make content understandable to search engines and users.

Hercules Dalianis, SU

Clinical text retrieval - some methods and some applications

Electronic patient records contain a waste source of information, both in form of structured information as diagnosis codes, drug codes, lab values, time stamps, etc and unstructured in form of free text. Methods - both rule based and machine learning based for retrieving this information is presented. Applications as diagnosis codes assignment, hospital acquired infection detection and adverse drug event detection will be discussed.

April 2815.15-18.00Gul, Orange, Röd Computer hall session Oral examination of Assignment 1,2,3 in front of computer May 513.15-15.00D3 Lecture 11: Guest lectures

Anders Friberg, KTH

Music Information Retrieval

The recent paradigm shift in music distribution has created a need for new methods of browsing, searching, and recommending music on the Internet. Given the size of current music databases, typically around 30 million songs or more, automatic methods are particularly useful. An overview of methods and challenges in the field with some snapshots from KTH research will be presented.

Magnus Sahlgren, Gavagai

Text analysis for Big Data

This lecture discusses some of the challenges we face when doing text analysis for Big Data. The lecture gives a brief overview of the technologies used by Gavagai, and touches upon notions such as Big Data, Text Analysis, Semantic Memories, and Deep Learning. We also give examples of real-world applications of text analysis.

Lecture 12: Guest lectures

CANCELLED May 2209.00-13.00Fantum, Lindstedtsv 24, floor 5 Project presentations Written report hand-inOral presentation in front of poster ¶