Schedule and course plan

Period 3 Where and When Activity Reading Examination January 1515.15-17.00E3 Lecture 1: Introduction, boolean retrieval, course practicalities Hedvig Kjellström, Johan Boye Manning Chapter 1, 2 January 1808.15-10.00D3 Lecture 2: Term vocabulary, dictionaries and tolerant retrievalJohan Boye Manning Chapter 2, 3 January 2215.15-17.00D3 Lecture 3: Index construction, index compressionJohan Boye Manning Chapter 4, 5 January 2915.00-18.00Spelhallen Computer hall sessionHedvig Kjellström, Johan Boye Oral examination of Assignment 1 in front of computer February 515.15-17.00D3 Lecture 4: Scoring, weighting, vector space modelHedvig Kjellström Manning Chapter 6, 7 February 810.15-12.00D3 Lecture 5: Retrieval of documents with hyperlinksJohan Boye, Hedvig Kjellström Manning Chapter 21Avrachenkov Sections 1-2 February 1510.15-12.00D3 Lecture 6: Evaluation, relevance feedback, query expansionHedvig Kjellström Manning Chapter 8, 9 February 1915.00-18.00Gul, Brun Computer hall sessionHedvig Kjellström, Johan Boye Oral examination of Assignment 2 in front of computer February 2613.15-15.00E3 Lecture 7: Probabilistic information retrieval, language modelsHedvig Kjellström Manning Chapter 11, 12 March 110.15-12.00D3 Lecture 8: Some useful additions to a search engine, Random IndexingViggo Kann Sahlgren Period 4 Where and When Activity Reading Examination March 1913.15-15.00D3 Lecture 9: Guest lectureMarkus Schedl, Johannes Kepler Universität, Austria An introduction to music information retrieval This lecture gives an introduction to Music Information Retrieval (MIR), a research field that is concerned with the extraction, analysis, and usage of information about any kind of music entity (for example, a song or a music artist) on any representation level (for example, audio signal, symbolic MIDI representation of a piece of music, or name of a music artist). We will first elaborate on the most common retrieval models to music collections (direct querying, query-by-example, browsing). Subsequently, we will review some fundamental concepts and methods of perceptual music feature extraction (foremost from text-based music context sources such as artist web pages or microblogs) and of similarity measurement, both of which are vital for a wide variety of MIR tasks. A categorization of factors that influence human music perception will be presented and some clues on how these aspects can be captured or inferred from low-level data will be given. Typical applications of MIR technology will be presented throughout the lecture to connect abstract methods and models to real-world applications. These include, for instance, automated playlist generation, music recommendation systems, fingerprinting systems such as Shazam, or intelligent music browsing interfaces. March 1915.00-18.00Spelhallen Computer hall sessionHedvig Kjellström, Johan Boye Oral examination of Assignment 3 in front of computer April 1210.15-12.00E3 Lecture 10: Retrieval of images in very large datasetsHedvig Kjellström April 1613.15-15.00D3 Lecture 11: Guest lectureFilip Radlinski, Microsoft Research Cambridge, UK Evaluating Search Engines Without Human Judgments How can you tell how well a search engine is performing? Traditional search engine evaluation takes a sample of search queries, fetches results, and manually assesses them. This approach often works well, but also poses a number of challenges. In particular, it can be difficult to be sure that the experts assessing queries really know what the users were looking for with a particular query, in the context of a particular time and place. In the competitive space on commercial search, these challenges can become huge. This lecture will consider some of the most difficult aspects of manually assessing search engine results, and contrast it with an alternative: observing the behavior of actual users. Search engine logs can record a great deal of user interaction data, and we will see some of the many ways that these interactions can be interpreted as feedback on search quality. The talk will consider the challenges and assumptions that different forms of online evaluation make, as well as methods that can be used to design online metrics that reflect user satisfaction most accurately and most efficiently. April 2315.15-16.00E3 Lecture 12: Guest lecture Oscar Täckström, SICS Sentiment Analysis In the last ten years, sentiment analysis has grown from a rather obscure sub-field of natural language processing to a highly productive and diverse field of research with a growing business impact. The basic assumption of all approaches to sentiment analysis is that we can learn something about people's attitudes towards other people, things and ideas, by looking at what they write or say about them. With the explosive growth of online media, such as blogs, micro-blogs and online fora, therefore comes a rich source of data from which we can learn more about people's attitudes and preferences. This knowledge, is fundamental to, for example, brand management and business intelligence, but may also find use in sociology and political science. In this lecture, I will give an overview of some important tasks and current approaches to sentiment analysis, focusing on the role of linguistic representations and tools from machine learning. Different levels of analysis requires different tools and I will spend some time discussing how to decide on the appropriate level and which tools to use for different levels. Specifically, I will discuss how one can create and use polarity lexicons, the limits of lexicon based approaches and if time permits, I will describe some recent work on using graphical models to model fine-grained sentiment in product reviews. May 310.15-11.00E3 Lecture 13: Guest lectureSimon Stenström, Findwise Information Retrieval and Findability The presentation will describe the process of building a search system rather than a search engine. There are many search engines out there, but the search engines are just one small part of creating a Findability solution. With a Findability solution we at Findwise mean both using the full potential of search technology and focusing on the four other critical dimensions of Findability; Business, Users, Information and Organization. This presentation will however focus on the technical parts such as the architecture of a search system. It will explain what we did to handle the real case search scenario at Uppsala University, starting at unstructured files ending up with a usable search system with an understandable user interface. You can see the result at http://search.uu.se/en/. May 1708.00-12.00Fantum, Lindstedtsv 24, floor 5 Project presentations Written report hand-inOral presentation in front of poster