Artificial Intelligence

Ileana Buhan

Aims
The objective is that participants in the course
are familiar with the classic retrieval models
understand the limitations and assumptions associated with these models
have insight and proficiency in the design and construction of search engines
are familiar with the standard evaluation methods for IR systems
are familiar with interaction techniques to support searchers in their quest for information
have an understanding of how the searcher's context and behaviour can be used to enhance retrieval effectiveness
have gained familiarity with recent scientific literature in this field

Content
While the rise of the internet has helped strengthen the field of Information Retrieval (IR), the area stretches far beyond plain web search, as a discipline situated between information science and computer science. In 1968, Gerard Salton defined information retrieval as "a field concerned with the structure, analysis, organization, storage, searching, and retrieval of information". Even though the area has seen many changes since that time and made a tremendous impact (who has never used a search engine?!), that definition is still accurate.
IR takes the notion of "relevance" as its core concept. As the scope of IR is limited to those cases where computers try to identify the relevance of information objects given a user's information need (as opposed to humans doing that, the common scenario in information science), perhaps "Computational Relevance" would have been a better term for the research in this area.
In this course, we cover the following aspects of Information Retrieval:
How do people search for information, and how can this be formalized?
How can we take advantage of term statistics, structure and annotations to capture the meaning of texts?
How can these elements be combined in order to find "relevant" information?
What techniques are necessary to scale to large text collections?