Title: Patent Information Retrieval
Instructors: Dr Mihai Lupu, Dr Allan Hanbury (TU Wien)
Date: 1st July, 9:30 - 13:30
Patents are legal documents issued by a government, which grants a set of rights of exclusivity and protection to the owner of an invention. As such, it is one of the main instruments of Intellectual Property protection, and a multi-billion dollar industry world-wide. For the IR researcher, it is an opportunity to investigate existing techniques and develop new methods for a domain which has IR at its very core. Any new invention or innovation, as well as the work of all academic or industry researchers, and of all patent searchers in every patent office across the world, revolves around the need to know exactly what has already been done and published before.
The total number of patents in force worldwide at the end of 2008 was approximately 6.7 million, with more that half a million new patents per year.
The tutorial aims to provide the IR researchers with an understanding of patent documents, how the patent system works, the challenges that patent searchers face in using the existing tools and in adopting new methods developed in academia. It covers work that has already been done applying IR, MT and ML methods in the patent domain. Finally, it will also introduce the participants to the evaluation of IR engines for the patent domain. The requirements of the professional users in this area are quite different from those of the general public, and we will discuss the use of Cranfield-based evaluation methods as well as the experience of more interactive evaluation efforts.
At the same time, the tutorial will inform the IR researcher about the unique opportunities that the patent domain provides: a large amount of multi-lingual and multi-modal documents, the widest possible span of covered domains, a highly annotated corpus and, very importantly, relevance judgements created by experts in the fields and recorded electronically in the documents.
Title: “Designing the Search Experience”
Instructor : Dr Tony Russel-Rose (UXLabs Ltd)
Date: 1st July, 14:30 - 18:30
The aim of this tutorial is to deliver a learning experience grounded in good scholarship, integrating the latest research findings with insights derived from the practical experience of designing and optimizing an extensive range of commercial search applications. It focuses on the development of transferable, practical skills that can be learnt and practiced within a half-day session.
Participants in this tutorial will:
- Explore the fundamental concepts and principles of Human-Centred Design for information search and discovery
- Study models of human information-seeking behavior (e.g. Bates, Belkin, Jarvelin & Ingwersen, Marchionini, Norman, Sutcliffe & Ennis, etc.), and how to apply interaction design principles based on those models
- Learn how to differentiate between various types of search behaviour: known-item, exploratory, lookup, learning, investigation, etc. and understand how they may be combined to form composite search strategies and patterns
- Develop an understanding of the key dimensions of user type, goal and mode of interaction, and how to apply these dimensions when designing for different user contexts
- Understand the role of design patterns, and how to apply UI design principles and patterns from various libraries in designing search user interfaces
- Gain an awareness of the key design resources available within the HCIR community and how to apply these to practical design challenges